© 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. 76455
    Prev
    Next
    INDEX
    Explanations

    URLs with query parameters

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

    The neuron is sensitive to numeric tokens and digit sequences (e.g. version numbers, IDs, and other number strings).

    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
     şart
    -0.78
    estima
    -0.75
     kurios
    -0.73
     Siege
    -0.73
    VOD
    -0.72
        
    -0.71
    Gön
    -0.71
     üzerinden
    -0.71
     Weyl
    -0.70
    essentially
    -0.69
    POSITIVE LOGITS
    /?
    2.39
    …?
    1.35
    ...?
    1.34
    ”?
    1.29
    "?
    1.28
    .?
    1.22
    ?
    1.15
    =?
    1.13
     "?
    1.03
    :?
    1.01
    Activations Density 0.075%

    No Known Activations