© 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. 65657
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    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
    __()
    -1.38
     studie
    -1.29
    stā
    -1.28
     футболка
    -1.27
     estrada
    -1.27
    owych
    -1.27
     polisi
    -1.26
     ralla
    -1.25
    €™
    -1.24
     бампер
    -1.24
    POSITIVE LOGITS
     there
    1.41
     with
    1.34
     resultar
    1.34
     sólidos
    1.23
     directamente
    1.21
    enuine
    1.20
     but
    1.20
    靭
    1.18
     establece
    1.18
     what
    1.16
    Activations Density 0.000%

    No Known Activations