© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30963
    Prev
    Next
    INDEX
    Explanations

    code structure separators

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

    The neuron selectively activates on numeric tokens (e.g. version numbers, dimensions, percentages, or any digit sequences).

    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
     regio
    -0.81
     ≤
    -0.77
    덕
    -0.71
     Vasco
    -0.71
     Waco
    -0.70
     efek
    -0.69
     FLEX
    -0.69
     تض
    -0.69
     EJ
    -0.69
     REVOL
    -0.68
    POSITIVE LOGITS
     ask
    0.79
    รู้สึก
    0.78
     bowel
    0.74
    ذه
    0.73
     diabetes
    0.73
     championship
    0.72
     insulin
    0.71
     Glove
    0.67
     midfield
    0.67
    bladder
    0.65
    Activations Density 0.051%

    No Known Activations