© 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. 84099
    Prev
    Next
    INDEX
    Explanations

    JavaScript ads and file paths

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

    The neuron fires on forward‐slash characters (e.g. path or diff separators “/”).

    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
     both
    -1.16
     probably
    -1.11
     supposedly
    -1.04
     those
    -1.02
     not
    -1.01
     formerly
    -1.00
     seemingly
    -0.99
     various
    -0.99
     perhaps
    -0.98
    敍
    -0.98
    POSITIVE LOGITS
     takie
    0.92
     súper
    0.88
    ≃
    0.87
     viennent
    0.86
     FUND
    0.86
     espectacular
    0.85
     أهم
    0.85
     mettent
    0.85
    enumii
    0.85
     QUICK
    0.85
    Activations Density 0.012%

    No Known Activations