© 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. 57910
    Prev
    Next
    INDEX
    Explanations

    report designation

    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
     (
    -1.02
    ↵↵
    -0.96
     '
    -0.92
     mysteries
    -0.88
     «
    -0.86
    clientY
    -0.85
     muito
    -0.85
    apatilla
    -0.84
     impose
    -0.83
     —
    -0.82
    POSITIVE LOGITS
     richied
    1.26
     melaporkan
    1.19
     settimane
    1.13
     poteva
    1.12
     avevano
    1.09
     فور
    1.06
     gioca
    1.03
    ることが
    1.02
     REPORTING
    1.02
     avrebbero
    1.02
    Activations Density 0.019%

    No Known Activations