© 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. 77863
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     here
    -1.14
     accesorio
    -1.06
    づけ
    -1.03
     trebuie
    -1.00
     باید
    -0.99
    taxia
    -0.95
    THIS
    -0.94
    Мини
    -0.93
    Here
    -0.93
    どうも
    -0.93
    POSITIVE LOGITS
    搅拌
    0.93
     then
    0.93
    7
    0.91
     myö
    0.90
     those
    0.86
     ľudí
    0.85
    crates
    0.85
     also
    0.83
     století
    0.82
    了自己
    0.79
    Activations Density 0.016%

    No Known Activations