© 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. 72177
    Prev
    Next
    INDEX
    Explanations

    possible and too

    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
     in
    -2.20
     There
    -2.09
     with
    -1.83
     Here
    -1.70
     will
    -1.64
    y
    -1.60
     while
    -1.56
     have
    -1.55
     F
    -1.54
     It
    -1.51
    POSITIVE LOGITS
     utiliser
    1.66
    indicates
    1.64
     wszystkich
    1.59
     mą
    1.56
    𓁹
    1.53
     avantages
    1.50
    jalá
    1.49
    estima
    1.49
    increases
    1.49
     москва
    1.48
    Activations Density 0.121%

    No Known Activations