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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7008
    Prev
    Next
    INDEX
    Explanations

    standard way

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

    The neuron responds to formal, procedural or policy‐style language—words you’d see in technical documentation, instructions, or legal/policy statements.

    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
     Такие
    0.72
     Работа
    0.71
     SDLK
    0.69
    ákat
    0.69
     Radioactive
    0.68
     空気
    0.66
    вичайно
    0.66
    ௭
    0.65
     えっと
    0.64
     posticis
    0.64
    POSITIVE LOGITS
    D
    0.88
    L
    0.86
     L
    0.80
    i
    0.80
    G
    0.78
    C
    0.78
     D
    0.77
    N
    0.75
    in
    0.75
    ar
    0.75
    Activations Density 0.464%

    No Known Activations