© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73943
    Prev
    Next
    INDEX
    Explanations

    Perspectives, pathways, visions, expressions, voices

    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
     zoude
    -1.73
     lyder
    -1.72
     براي
    -1.72
     レスト
    -1.67
    良いです
    -1.63
     avancer
    -1.63
    鳚
    -1.63
     reager
    -1.61
    NATIONAL
    -1.60
    ꯷
    -1.59
    POSITIVE LOGITS
     in
    2.33
     of
    1.93
     a
    1.91
     as
    1.84
     through
    1.84
     \&
    1.77
     и
    1.67
     on
    1.66
     και
    1.65
     And
    1.64
    Activations Density 0.090%

    No Known Activations