© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12125
    Prev
    Next
    INDEX
    Explanations

    compulsive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    an
    1.64
     همچ
    1.46
    rü
    1.44
    a
    1.41
    yszer
    1.39
    r
    1.37
    underset
    1.34
    眾
    1.32
    much
    1.30
    lig
    1.26
    POSITIVE LOGITS
    DisplayName
    1.61
    okkal
    1.52
     এছাড়া
    1.51
     teaming
    1.48
    Generally
    1.43
     ebb
    1.39
    сили
    1.37
    앰
    1.35
    endTime
    1.34
    ಡಿ
    1.34
    Activations Density 0.001%

    No Known Activations