© 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. 20568
    Prev
    Next
    INDEX
    Explanations

    scrutiny and close examination

    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_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
     Interestingly
    -2.86
     Presumably
    -2.67
     Apparently
    -2.67
     Primarily
    -2.64
     Perhaps
    -2.56
     Either
    -2.56
     Especially
    -2.52
     Somewhat
    -2.48
     Evidently
    -2.48
     Placing
    -2.47
    POSITIVE LOGITS
    0
    2.95
    1
    2.34
    able
    2.20
    no
    2.16
    an
    2.08
    塒
    2.08
    7
    2.06
    '
    2.03
    the
    2.00
    m
    2.00
    Activations Density 0.003%

    No Known Activations