© 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. 64187
    Prev
    Next
    INDEX
    Explanations

    Puerto Rico, Arkansas, former

    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
    uacute
    -0.69
    PREDICT
    -0.69
    Fow
    -0.67
    gá
    -0.66
    ዘ
    -0.65
    gregor
    -0.65
    ھیے
    -0.64
     različ
    -0.63
    rawValue
    -0.62
    超級
    -0.62
    POSITIVE LOGITS
    érations
    0.78
     Alice
    0.76
     SCH
    0.73
    nagyobb
    0.69
     neste
    0.68
    veys
    0.67
    CONTR
    0.67
    fts
    0.65
     అ
    0.65
    Ashley
    0.64
    Activations Density 0.065%

    No Known Activations