© 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. 86767
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis and semicolon

    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
    ’
    -1.77
    ”-
    -1.55
    ”:
    -1.50
    芣
    -1.48
    ”,
    -1.47
    -<
    -1.45
    </
    -1.45
     disputa
    -1.44
    逦
    -1.44
    マヨ
    -1.41
    POSITIVE LOGITS
     or
    1.78
     "
    1.52
     fossero
    1.47
     when
    1.42
     going
    1.41
     mehrerer
    1.41
     głównie
    1.41
     numerosas
    1.40
     ponownie
    1.40
     maravillas
    1.37
    Activations Density 0.006%

    No Known Activations