© 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. 31776
    Prev
    Next
    INDEX
    Explanations

    play followed by a related term

    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
     planejamento
    -0.87
    ﾄ
    -0.84
    ionado
    -0.80
    isFile
    -0.77
    ью
    -0.75
    つける
    -0.75
    šo
    -0.73
    claimers
    -0.73
    餮
    -0.71
     desenho
    -0.70
    POSITIVE LOGITS
    doh
    1.33
    fulness
    1.21
     doh
    1.13
    indelijk
    1.06
     havoc
    1.04
     offs
    1.03
    bill
    0.98
    maker
    0.97
    Doh
    0.94
    tester
    0.92
    Activations Density 0.024%

    No Known Activations