© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41650
    Prev
    Next
    INDEX
    Explanations

    quoted text or names

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

    The neuron is picking up on formatting delimiters (especially quotation‐mark tokens, block separator lines like “======”, and related punctuation that mark quoted or separated text).

    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
    '
    -2.19
     with
    -2.02
     on
    -2.02
     from
    -2.00
     out
    -1.92
     where
    -1.83
     in
    -1.78
     A
    -1.73
     M
    -1.72
     B
    -1.68
    POSITIVE LOGITS
    																											
    1.84
    																												
    1.81
     termica
    1.78
    																														
    1.72
     ronda
    1.71
     plafon
    1.71
     consulter
    1.69
    Groet
    1.68
    ///////////////
    1.68
    Höhe
    1.67
    Activations Density 0.027%

    No Known Activations