© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64666
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

    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_22/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
     where
    -1.78
     because
    -1.73
     after
    -1.72
     that
    -1.71
     should
    -1.60
     on
    -1.55
     before
    -1.53
     at
    -1.49
     it
    -1.45
     when
    -1.45
    POSITIVE LOGITS
     verschillende
    1.76
     différentes
    1.60
     a
    1.58
     dwóch
    1.44
     két
    1.41
     trzech
    1.41
     réfrig
    1.38
     vijf
    1.38
     FOUR
    1.36
     trois
    1.33
    Activations Density 0.107%

    No Known Activations