© 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. 30508
    Prev
    Next
    INDEX
    Explanations

    FOR PUBLICATION

    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
    ?»
    -1.10
    grandchildren
    -1.05
    ）」
    -1.05
    lllllllll
    -1.04
    llllllll
    -1.03
     rokok
    -1.00
    Frankreich
    -0.97
    👹
    -0.97
    ició
    -0.96
     Utama
    -0.94
    POSITIVE LOGITS
     anymore
    1.27
     actuellement
    1.09
     nor
    1.05
    而是
    1.05
     sondern
    0.99
    也得
    0.97
    ఱ
    0.97
     ไม่
    0.96
     puede
    0.90
     incluye
    0.89
    Activations Density 0.043%

    No Known Activations