© 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-16K
    7. 2252
    Prev
    Next
    INDEX
    Explanations

    recommendations and advice

    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_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
    готовить
    2.98
     filo
    2.96
    ْع
    2.74
    ی
    2.73
    깐
    2.68
    дцать
    2.63
    رک
    2.62
    OURCE
    2.61
    на
    2.61
    స్
    2.57
    POSITIVE LOGITS
     Inference
    2.88
    Attractive
    2.86
    િ
    2.80
    f
    2.80
    𝐡
    2.77
    quele
    2.70
    ით
    2.69
    edly
    2.66
     такая
    2.63
    િસ
    2.60
    Activations Density 0.246%

    No Known Activations