© 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. 10-GEMMASCOPE-RES-131K
    7. 44719
    Prev
    Next
    INDEX
    Explanations

    through or between

    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
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.56
    はこの
    -1.33
     in
    -1.23
    ционного
    -1.20
     tais
    -1.20
     on
    -1.17
    のことを
    -1.17
     WITHIN
    -1.15
    niego
    -1.15
     promen
    -1.15
    POSITIVE LOGITS
     recurrir
    1.34
    ádza
    1.34
     soñar
    1.32
     étn
    1.31
     transportar
    1.30
     piernas
    1.30
     machte
    1.30
    𞤢
    1.29
     kolory
    1.29
     quieren
    1.29
    Activations Density 0.004%

    No Known Activations