© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7132
    Prev
    Next
    INDEX
    Explanations

    balanced formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     துய்யமணி
    1.33
    ꗕ
    1.30
    <unused1423>
    1.30
    <pad>
    1.30
     sakamm
    1.30
    渦柱
    1.30
    smoio
    1.30
    HtIdx
    1.30
    𒌧
    1.30
    𒅊
    1.30
    POSITIVE LOGITS
    -
    0.77
     and
    0.75
     del
    0.74
    के
    0.73
    ball
    0.72
    2
    0.72
    4
    0.71
    चंद
    0.69
    त
    0.68
    ín
    0.68
    Activations Density 0.000%

    No Known Activations