© 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. 103814
    Prev
    Next
    INDEX
    Explanations

    headings or titles

    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
     kerosene
    -0.71
     Mag
    -0.71
    жли
    -0.71
     Flächen
    -0.70
    träd
    -0.69
     Eisen
    -0.67
    ╤
    -0.67
     roboc
    -0.67
    TAGS
    -0.66
     BSEB
    -0.66
    POSITIVE LOGITS
     markets
    1.01
    markets
    1.00
     Markets
    0.94
    market
    0.94
     Simplified
    0.90
     obrazy
    0.84
    Markets
    0.82
    Paging
    0.81
    idać
    0.81
     Paging
    0.81
    Activations Density 0.004%

    No Known Activations