© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    gap

    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
    ج
    1.41
    ли
    1.35
    ে
    1.22
    fptr
    1.11
     forgo
    1.11
    ,*/}*.
    1.09
    SpriteCollision
    1.08
    ட்சத்திர
    1.07
    ℠
    1.07
    httpClient
    1.06
    POSITIVE LOGITS
    一个
    1.11
    ır
    1.09
    на
    1.04
    ıyla
    1.04
    不是
    1.02
    ín
    0.98
    です
    0.98
    }])
    0.97
    を実現
    0.96
    ৯
    0.96
    Activations Density 0.003%

    No Known Activations