© 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. 104781
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    indentation or whitespace at the beginning of lines in source code.

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

    The neuron activates on numeric literals (integers and decimals) in the 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
    u
    -2.19
    k
    -2.02
    p
    -1.95
    m
    -1.94
    y
    -1.91
    c
    -1.84
     p
    -1.83
     While
    -1.81
     from
    -1.79
    r
    -1.78
    POSITIVE LOGITS
    moderne
    1.77
    齜
    1.73
     baden
    1.72
    鹩
    1.70
     gewicht
    1.70
     estadía
    1.67
    their
    1.65
     zand
    1.64
    
    1.63
    ﻹ
    1.63
    Activations Density 0.015%

    No Known Activations