© 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. 93395
    Prev
    Next
    INDEX
    Explanations

    starting sequences like "Indycar", "1.", "Q:"

    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
    文獻
    -0.85
    ದು
    -0.82
     faveur
    -0.78
     this
    -0.76
     bebas
    -0.75
     fame
    -0.71
     additional
    -0.70
     which
    -0.68
     warrant
    -0.67
    STRUCTIONS
    -0.67
    POSITIVE LOGITS
     vec
    1.73
    vec
    1.54
    format
    1.10
     format
    1.01
    include
    0.91
     Default
    0.85
    EVERY
    0.84
    stringify
    0.84
     [].
    0.83
    "".
    0.82
    Activations Density 0.007%

    No Known Activations