© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47437
    Prev
    Next
    INDEX
    Explanations

    special prefixes followed by code

    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
    ┐
    -0.80
    ɚ
    -0.78
    гут
    -0.75
    österreich
    -0.75
    Hvem
    -0.75
    PutMapping
    -0.75
    𝓵
    -0.73
    ophenyl
    -0.73
    修復
    -0.72
    )}$
    -0.71
    POSITIVE LOGITS
     tracking
    0.93
    tracking
    0.86
     tracks
    0.86
     Inverse
    0.85
    Latex
    0.85
    compute
    0.84
     தே
    0.84
    track
    0.83
     Tracking
    0.78
    NSIndexPath
    0.78
    Activations Density 0.010%

    No Known Activations