© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3303
    Prev
    Next
    INDEX
    Explanations

    from ... to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    вая
    0.80
     Fácil
    0.80
     Hrvatske
    0.79
    esquerdo
    0.73
    ಾಟ
    0.73
    婺
    0.73
    プション
    0.72
    付き
    0.72
    嶽
    0.71
    ください
    0.70
    POSITIVE LOGITS
    aad
    0.81
    But
    0.74
    hile
    0.73
    However
    0.71
    ،
    0.71
    And
    0.69
    kurs
    0.69
    ll
    0.69
    lagen
    0.68
    Vector
    0.68
    Activations Density 0.001%

    No Known Activations