© 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. 78392
    Prev
    Next
    INDEX
    Explanations

    cursor and systems

    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
    liter
    -0.75
     rów
    -0.73
    镍
    -0.71
    ことになる
    -0.71
    ialog
    -0.69
    リッシュ
    -0.68
     event
    -0.68
     fuerzas
    -0.68
    Pourquoi
    -0.68
    olated
    -0.67
    POSITIVE LOGITS
     Curs
    1.20
    Cursors
    0.95
     cursor
    0.89
    ɞ
    0.88
     sura
    0.86
     curs
    0.84
     cresc
    0.79
     DMS
    0.78
     cruz
    0.77
     Courant
    0.76
    Activations Density 0.001%

    No Known Activations