© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36161
    Prev
    Next
    INDEX
    Explanations

    column fields names

    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_12_width_262k_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
    We
    1.00
     .
    0.91
    4
    0.91
    1
    0.91
    In
    0.90
    And
    0.89
    o
    0.88
    +
    0.88
    MA
    0.86
    V
    0.86
    POSITIVE LOGITS
     concetto
    1.05
     precisión
    1.02
    字段
    1.02
    descripcion
    1.00
     testimonial
    0.99
    flächen
    0.99
     вопросов
    0.98
    欄
    0.98
     değişken
    0.98
     යුතු
    0.96
    Activations Density 0.455%

    No Known Activations