© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79223
    Prev
    Next
    INDEX
    Explanations

    technical documentation or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Particularly
    -0.83
    Wre
    -0.80
    翌日
    -0.77
    没错
    -0.74
    发生的
    -0.74
    Пока
    -0.72
     wirklich
    -0.71
    Pillow
    -0.70
    不久
    -0.69
    pillow
    -0.69
    POSITIVE LOGITS
     Member
    0.90
    мент
    0.81
    же
    0.80
     dị
    0.79
     ginge
    0.76
    huur
    0.75
    numer
    0.75
     ADVIS
    0.72
     neer
    0.72
     Gender
    0.71
    Activations Density 0.002%

    No Known Activations