© 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. 22596
    Prev
    Next
    INDEX
    Explanations

    negotiable and refundable

    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
     continue
    -1.49
     Brunnen
    -1.47
    瞜
    -1.45
     judicia
    -1.42
     agresión
    -1.41
    íte
    -1.37
     ktoré
    -1.36
     Zwiebel
    -1.31
     continues
    -1.30
     realise
    -1.30
    POSITIVE LOGITS
    <strong>
    1.53
    性和
    1.20
     podob
    1.12
    <code>
    1.10
    whitespace
    1.09
    .
    1.09
     angep
    1.09
    置いて
    1.08
    tably
    1.06
     sunny
    1.05
    Activations Density 0.015%

    No Known Activations