© 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. 10-GEMMASCOPE-RES-131K
    7. 111631
    Prev
    Next
    INDEX
    Explanations

    `[` `{` `(` `.` `#` `leak`

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

    whitespace followed by structural or formatting separators in code and documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on numeric tokens (numbers, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    艄
    -2.56
    蹀
    -2.44
     ligeramente
    -2.41
     But
    -2.39
     renowned
    -2.31
     этого
    -2.31
     verdaderamente
    -2.30
     magnificent
    -2.23
     famed
    -2.19
     posiblemente
    -2.19
    POSITIVE LOGITS
     in
    3.14
     nearing
    2.27
     conseguido
    2.19
    t
    2.16
     at
    2.16
    มากๆ
    2.08
     when
    2.00
    诤
    1.99
    when
    1.99
     preguntó
    1.98
    Activations Density 0.001%

    No Known Activations