© 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. 44514
    Prev
    Next
    INDEX
    Explanations

    privacy and private spaces

    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
     are
    -1.95
    aimeJ
    -1.77
     Unglück
    -1.72
     aparecer
    -1.57
     Nichts
    -1.55
     harán
    -1.53
    -1.52
     universitaria
    -1.52
     asisten
    -1.49
    旆
    -1.49
    POSITIVE LOGITS
    Хотя
    1.98
    /"
    1.94
    昞
    1.84
    and
    1.82
    ⑊
    1.79
     eget
    1.77
     "
    1.70
    Даже
    1.69
    Однако
    1.66
    鳢
    1.65
    Activations Density 0.010%
    No Known Activations