© 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-16K
    7. 5989
    Prev
    Next
    INDEX
    Explanations

    search, document, highlight, interactive, $

    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_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
    ه
    2.31
    ン
    2.22
     únic
    2.11
    ﺏ
    2.06
    Про
    2.02
    🅔
    2.02
    🅐
    1.98
    看来
    1.92
     fato
    1.91
     kemudian
    1.91
    POSITIVE LOGITS
    ים
    3.16
    ي
    3.16
    y
    3.00
    েরই
    2.89
    s
    2.89
    та
    2.88
    ের
    2.81
    ung
    2.67
    ers
    2.66
    ल
    2.53
    Activations Density 0.108%

    No Known Activations