© 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. 34-GEMMASCOPE-RES-131K
    7. 58642
    Prev
    Next
    INDEX
    Explanations

    inventor, level, AMD, CODE, crypto

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

    This neuron detects long sequences of uppercase letters, digits, and underscores typical of code identifiers or macros.

    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
    tokenizer
    -0.73
     桥
    -0.70
    ilu
    -0.67
     αυτο
    -0.66
     olympique
    -0.66
     manifests
    -0.66
    erk
    -0.65
     bitcoin
    -0.65
     legacy
    -0.65
     heard
    -0.64
    POSITIVE LOGITS
     Mon
    0.86
    destinations
    0.82
     RING
    0.82
     emplace
    0.79
     mon
    0.79
     Riders
    0.75
    浇
    0.75
    Mon
    0.75
    zule
    0.74
     abe
    0.73
    Activations Density 0.031%

    No Known Activations