© 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. 34-GEMMASCOPE-RES-131K
    7. 108363
    Prev
    Next
    INDEX
    Explanations

    Lip Tars

    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
    isiones
    -0.79
     بهره
    -0.79
     volgens
    -0.79
     alimentare
    -0.77
     целе
    -0.73
     ซ
    -0.72
     einschließlich
    -0.72
    consola
    -0.72
     Gogh
    -0.71
    omm
    -0.71
    POSITIVE LOGITS
     говоря
    0.80
    ᆼ
    0.78
    後に
    0.78
    nimo
    0.75
     wrecked
    0.74
    嚥
    0.71
     fastened
    0.71
     wrecks
    0.70
     detuvo
    0.70
     munch
    0.69
    Activations Density 0.903%

    No Known Activations