© 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. 10-GEMMASCOPE-RES-131K
    7. 127960
    Prev
    Next
    INDEX
    Explanations

    periods of time

    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_10/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
    泐
    -2.09
    coledì
    -2.08
    VPB
    -1.98
     начинают
    -1.89
    était
    -1.88
    
    -1.85
    pecabe
    -1.84
    筈
    -1.84
    ’;
    -1.83
     emozioni
    -1.82
    POSITIVE LOGITS
    \
    2.64
    I
    2.05
     AND
    1.95
    en
    1.94
    (
    1.91
    le
    1.84
    a
    1.83
     meiner
    1.82
    ти
    1.80
    我们的
    1.80
    Activations Density 0.067%

    No Known Activations