© 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. 34-GEMMASCOPE-RES-131K
    7. 91133
    Prev
    Next
    INDEX
    Explanations

    serialization FML model testing util cli

    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_34/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
     common
    -0.99
    Einfach
    -0.89
     迷
    -0.88
    Kenn
    -0.85
    common
    -0.85
     wła
    -0.84
    ulir
    -0.84
    Trotz
    -0.83
    Süd
    -0.82
    accom
    -0.82
    POSITIVE LOGITS
     Ibiza
    0.87
     रुप
    0.85
     tomes
    0.83
    𝟵
    0.82
    hi
    0.82
    even
    0.82
     immers
    0.82
    ech
    0.81
    ui
    0.81
    will
    0.80
    Activations Density 0.022%

    No Known Activations