© 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. 63577
    Prev
    Next
    INDEX
    Explanations

    getting string data

    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
    BufferSize
    -0.75
    AsStream
    -0.73
     errno
    -0.72
    桝
    -0.70
    intValue
    -0.70
    跟你
    -0.70
     judging
    -0.69
     score
    -0.69
    parseInt
    -0.69
    FieldOffset
    -0.69
    POSITIVE LOGITS
    ToString
    2.02
     ToString
    1.62
     toString
    1.59
    getStringExtra
    1.48
    toString
    1.46
    getString
    1.44
    String
    1.37
    GetString
    1.30
    NSString
    1.23
    AsString
    1.23
    Activations Density 0.022%

    No Known Activations