© 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. 1598
    Prev
    Next
    INDEX
    Explanations

    theory and scene

    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
    an
    3.41
    d
    3.33
    dür
    3.17
    ა
    2.86
    m
    2.86
     lifetimes
    2.76
    nya
    2.74
    t
    2.66
    we
    2.66
    y
    2.62
    POSITIVE LOGITS
    jší
    2.85
     formic
    2.72
    itary
    2.66
    𝙚
    2.66
    𝙖
    2.63
    ा
    2.60
    +}$
    2.60
    ئی
    2.56
    ######
    2.50
    ඥ
    2.47
    Activations Density 0.372%

    No Known Activations