© 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. 34-GEMMASCOPE-RES-131K
    7. 86845
    Prev
    Next
    INDEX
    Explanations

    slider, disabled, color

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

    This neuron detects programming-or code-related tokens (identifiers, file extensions, punctuation, version numbers, CSS/HTML attributes, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     waistband
    -0.75
    んご
    -0.71
     ^=
    -0.71
     Vang
    -0.71
    Զ
    -0.70
     copier
    -0.68
    MemberId
    -0.68
    入る
    -0.67
    情報の
    -0.67
    Headline
    -0.66
    POSITIVE LOGITS
     track
    1.16
     thumb
    1.10
    track
    1.07
    Thumb
    1.00
    ыре
    0.98
     slider
    0.98
     Thumb
    0.96
    Track
    0.93
    TRACK
    0.92
    thumb
    0.90
    Activations Density 0.008%

    No Known Activations