© 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. 9507
    Prev
    Next
    INDEX
    Explanations

    Hermann Grassmann, United Nations

    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
     for
    -1.73
     first
    -1.69
     eight
    -1.48
     or
    -1.46
     at
    -1.45
     three
    -1.42
    *
    -1.42
     some
    -1.38
     if
    -1.36
     only
    -1.36
    POSITIVE LOGITS
    仕上が
    1.56
     autonomie
    1.53
    OBJETIVOS
    1.52
    ೦
    1.52
     verhind
    1.49
     Ähnliche
    1.49
     terce
    1.47
    CONCLUSIONES
    1.45
     ativar
    1.44
    そういった
    1.43
    Activations Density 0.004%

    No Known Activations