© 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. 110611
    Prev
    Next
    INDEX
    Explanations

    believe it or me

    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
    \
    -1.82
    t
    -1.77
    f
    -1.68
    m
    -1.64
    S
    -1.59
    at
    -1.59
    -/
    -1.58
    I
    -1.55
    ı
    -1.54
    \_
    -1.53
    POSITIVE LOGITS
    坨
    1.71
    Another
    1.55
     offrent
    1.53
    There
    1.50
     interrom
    1.49
     могут
    1.49
    𐤔
    1.49
     todavía
    1.48
    私たちの
    1.48
     there
    1.47
    Activations Density 0.006%

    No Known Activations