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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98663
    Prev
    Next
    INDEX
    Explanations

    variable declarations and assignments

    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
     from
    -2.08
     this
    -2.03
     by
    -1.87
     with
    -1.71
     that
    -1.68
     because
    -1.66
     only
    -1.66
     and
    -1.63
     When
    -1.63
     there
    -1.60
    POSITIVE LOGITS
     nivå
    1.38
     corriger
    1.37
     commencer
    1.31
     acides
    1.29
     många
    1.28
     résultats
    1.27
     evoc
    1.24
    Tues
    1.23
     imprimer
    1.23
     constater
    1.21
    Activations Density 0.007%

    No Known Activations