© 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-16K
    7. 1004
    Prev
    Next
    INDEX
    Explanations

    4 followed by 5

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vs
    0.84
     once
    0.83
     des
    0.77
     versus
    0.76
     whether
    0.75
     (
    0.74
     specifically
    0.74
     distinct
    0.72
     concurrent
    0.71
     the
    0.70
    POSITIVE LOGITS
    <unused35>
    1.07
    <unused1957>
    1.03
    鏤
    1.01
    ंपूर्
    0.99
    㣩
    0.96
    悛
    0.96
    <unused1160>
    0.96
    <unused1991>
    0.96
    <unused1783>
    0.95
    <unused2102>
    0.93
    Activations Density 0.187%

    No Known Activations