© 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. 63533
    Prev
    Next
    INDEX
    Explanations

    read/write operations

    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
    riction
    -0.78
     formazione
    -0.73
    ThemeOverlay
    -0.69
    reshed
    -0.69
    外線
    -0.69
     Übere
    -0.69
    емая
    -0.68
     linkage
    -0.68
     Aufg
    -0.67
    ㅘ
    -0.67
    POSITIVE LOGITS
     write
    3.63
     read
    3.08
    write
    2.89
    WRITE
    2.86
     writing
    2.78
     writes
    2.67
     Write
    2.66
     WRITE
    2.66
    Write
    2.63
     reading
    2.44
    Activations Density 0.129%

    No Known Activations