© 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. 98837
    Prev
    Next
    INDEX
    Explanations

    reports of statements

    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
    u
    -1.13
    this
    -1.07
    という
    -1.04
    m
    -1.02
    ob
    -1.01
    ń
    -1.00
     queste
    -0.99
    この
    -0.98
     barnet
    -0.98
     tämän
    -0.97
    POSITIVE LOGITS
     in
    2.00
     would
    1.43
     there
    1.41
     during
    1.37
     on
    1.31
     at
    1.20
    Teks
    1.13
     seper
    1.07
     it
    1.04
    acakt
    1.04
    Activations Density 0.054%

    No Known Activations