© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    mouse scroll back

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

    The neuron flags “content” words—i.e. non‐stopword nouns, verbs, and adjectives—rather than common function words.

    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
    -
    0.75
    서
    0.71
    的には
    0.71
    :
    0.70
    ם
    0.70
    ;
    0.67
    ও
    0.66
    靈
    0.66
    র
    0.65
    데
    0.64
    POSITIVE LOGITS
     trasera
    0.88
     árboles
    0.85
    ahah
    0.84
     beneficiaries
    0.82
     trabalhadores
    0.82
     clasificación
    0.82
     bosques
    0.82
     vertices
    0.81
    employees
    0.81
    ുന്ന
    0.80
    Activations Density 0.000%

    No Known Activations