© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145348
    Prev
    Next
    INDEX
    Explanations

    compression, noise, serious

    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_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    0.68
     regional
    0.68
    bery
    0.64
    bees
    0.64
    ماً
    0.63
    ed
    0.62
    iber
    0.61
    bad
    0.60
     frustrated
    0.59
    err
    0.58
    POSITIVE LOGITS
    𝟘
    0.87
    xcuserdata
    0.80
    🪜
    0.77
    不去
    0.76
     orderBy
    0.75
     patham
    0.75
    Identifier
    0.75
    𝔾
    0.75
    ણામ
    0.73
    Transforms
    0.73
    Activations Density 0.001%

    No Known Activations