© 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. 12428
    Prev
    Next
    INDEX
    Explanations

    **structure quantification definitions**

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

    The neuron fires on passages giving direct instructions or addressing “you” (i.e. second‐person calls to action or advice).

    oai_token-act-pair · o4-miniTriggered 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
    ي
    0.89
    y
    0.88
    k
    0.76
    ka
    0.72
    okinetic
    0.70
    or
    0.70
    无比
    0.69
    ्वान
    0.68
    ви
    0.66
    дови
    0.66
    POSITIVE LOGITS
     ρ
    0.95
     dakkh
    0.91
    irthday
    0.91
     pratis
    0.90
    akkhan
    0.90
     giải
    0.89
     szerző
    0.89
    시키
    0.89
     kanggo
    0.89
    }$-
    0.88
    Activations Density 0.000%

    No Known Activations