© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12041
    Prev
    Next
    INDEX
    Explanations

    javascript PropTypes definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    colons in structured data formats like JSON, code, or data dictionaries.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     gefe
    -1.60
    wendig
    -1.56
    ଢ
    -1.50
    ⢣
    -1.45
     musiciens
    -1.44
    wendige
    -1.39
    richtungen
    -1.38
     soldadura
    -1.35
    chage
    -1.34
     Parece
    -1.34
    POSITIVE LOGITS
     also
    1.81
     on
    1.79
    0
    1.73
    m
    1.53
    s
    1.52
     as
    1.50
    2
    1.45
    f
    1.43
    v
    1.41
    V
    1.38
    Activations Density 0.045%

    No Known Activations