© 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. 107892
    Prev
    Next
    INDEX
    Explanations

    events and stages

    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
     Gattung
    -1.08
     spune
    -0.95
    periodic
    -0.88
     після
    -0.88
    幸いです
    -0.87
    你先
    -0.85
     CONSIDER
    -0.84
     atunci
    -0.83
     &
    -0.82
     directivos
    -0.82
    POSITIVE LOGITS
     date
    1.20
     berlangsung
    1.02
     مباشرة
    1.00
     شدن
    0.96
    beginn
    0.96
     дату
    0.93
    ition
    0.93
    NewUrlParser
    0.92
    OrUpdate
    0.89
     xong
    0.85
    Activations Density 0.150%

    No Known Activations