© 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. 10-GEMMASCOPE-RES-131K
    7. 114146
    Prev
    Next
    INDEX
    Explanations

    in this / which

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     a
    -2.30
    dámské
    -1.56
     “
    -1.50
     falando
    -1.46
    dáms
    -1.40
     adecuado
    -1.38
     aumentare
    -1.36
     campanha
    -1.32
    、“
    -1.30
    ("
    -1.30
    POSITIVE LOGITS
     to
    1.93
     SOMEONE
    1.47
     selalu
    1.33
    abinieri
    1.30
     إلى
    1.30
    要用
    1.26
     asus
    1.23
    няют
    1.20
     gives
    1.20
     RESULT
    1.19
    Activations Density 0.137%

    No Known Activations