© 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. 30445
    Prev
    Next
    INDEX
    Explanations

    check out

    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
    поді
    -0.87
    lässlich
    -0.86
    rying
    -0.85
     erhielt
    -0.85
     fausse
    -0.84
    篮球
    -0.82
     proceed
    -0.82
    athie
    -0.82
    strains
    -0.80
     sentido
    -0.79
    POSITIVE LOGITS
     out
    2.69
     check
    2.42
    Check
    2.23
    check
    2.19
     Check
    2.05
     CHECK
    1.80
     checking
    1.76
    チェック
    1.61
     checked
    1.60
    CHECK
    1.55
    Activations Density 0.007%

    No Known Activations