© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6190
    Prev
    Next
    INDEX
    Explanations

    sunlight passes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on past‐participle verbs (words ending in “-ed”) indicating passive or completed actions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "provided" in informational or reference contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    past-participle verbs used in passive or post-nominal participial constructions (e.g., “is/are …” or “noun + participle” patterns).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    다
    0.79
    ded
    0.73
    ا
    0.68
    ce
    0.67
    úc
    0.67
    ưng
    0.67
    }}=$
    0.67
    ㅠ
    0.66
    الي
    0.65
    paredStatement
    0.65
    POSITIVE LOGITS
     acesta
    0.91
    ROR
    0.89
    Karen
    0.84
     rips
    0.84
     LAKE
    0.83
     anisot
    0.81
     Оксана
    0.80
     Karen
    0.80
     Darren
    0.79
     ఇటీ
    0.79
    Activations Density 0.001%

    No Known Activations