© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    one or more

    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
    ั่น
    -0.93
     fuper
    -0.91
    一千
    -0.87
    իս
    -0.87
    amese
    -0.85
     obfer
    -0.84
    XXII
    -0.81
     neceff
    -0.81
    Wider
    -0.81
     occafion
    -0.81
    POSITIVE LOGITS
     one
    4.06
     één
    2.44
    One
    2.20
     одного
    2.17
    หนึ่ง
    2.11
     один
    2.08
     ONE
    2.03
     одну
    1.86
    one
    1.84
     jednego
    1.83
    Activations Density 0.281%

    No Known Activations