© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13470
    Prev
    Next
    INDEX
    Explanations

    redistribution and use with or without modification

    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
    ⻓
    -1.56
     limitaciones
    -1.43
     reuniones
    -1.40
    mathrm
    -1.30
     hornear
    -1.30
    ࿚
    -1.28
    多种
    -1.27
     conductas
    -1.25
     devra
    -1.25
    However
    -1.25
    POSITIVE LOGITS
     as
    1.84
     by
    1.83
     for
    1.74
     were
    1.47
     they
    1.38
     no
    1.34
     until
    1.34
    -
    1.33
     “
    1.33
     it
    1.25
    Activations Density 0.137%

    No Known Activations