© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129286
    Prev
    Next
    INDEX
    Explanations

    just like

    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_10/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
    )))),
    -1.84
    ⚌
    -1.81
    quilibrium
    -1.80
    tronlink
    -1.78
    AutoScaleMode
    -1.77
    iric
    -1.75
    abinieri
    -1.73
     IBRARY
    -1.73
    cordova
    -1.70
    lería
    -1.68
    POSITIVE LOGITS
    :
    1.95
    //
    1.88
    <
    1.84
    いかがでしたか
    1.82
     how
    1.74
     include
    1.65
     other
    1.56
    与此
    1.55
    /
    1.55
     it
    1.54
    Activations Density 0.008%

    No Known Activations