© 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. 22-GEMMASCOPE-RES-131K
    7. 25922
    Prev
    Next
    INDEX
    Explanations

    foreign code snippets

    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_22/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
    了我
    -1.16
     държа
    -1.09
    Leírás
    -1.07
     silikon
    -1.06
    dengan
    -1.02
     kalori
    -1.01
     gancho
    -1.00
    〬
    -0.98
     équilibre
    -0.96
     göm
    -0.96
    POSITIVE LOGITS
    ('
    0.98
     get
    0.96
     solicit
    0.95
    Odkazy
    0.91
     begin
    0.90
     начал
    0.90
     obituary
    0.87
    ādi
    0.87
    ерез
    0.86
     his
    0.86
    Activations Density 0.003%

    No Known Activations