© 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. 128274
    Prev
    Next
    INDEX
    Explanations

    function definitions and method calls

    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
    Continu
    -1.26
    Aplica
    -1.23
    Dossier
    -1.21
    karten
    -1.20
     mortem
    -1.19
    Grup
    -1.18
    Ressources
    -1.17
     innumer
    -1.16
     substan
    -1.14
     signif
    -1.14
    POSITIVE LOGITS
     with
    1.88
     using
    1.82
     by
    1.73
     two
    1.65
     four
    1.34
     six
    1.34
     three
    1.30
     December
    1.30
     on
    1.28
     now
    1.27
    Activations Density 0.026%

    No Known Activations