© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66839
    Prev
    Next
    INDEX
    Explanations

    additional points or clarifications

    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
     eerste
    -1.45
     pertama
    -1.23
    jící
    -1.16
     asemenea
    -1.12
     pierws
    -1.11
     nguoi
    -1.10
     první
    -1.06
    เพราะ
    -1.06
     funcionarios
    -1.06
     jego
    -1.05
    POSITIVE LOGITS
     if
    1.48
     If
    1.38
    Переваги
    1.23
    Aunque
    1.15
    Occasionally
    1.14
    Although
    1.09
     Note
    1.09
    There
    1.07
     Since
    1.06
     prevent
    1.05
    Activations Density 0.017%

    No Known Activations