© 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. 108529
    Prev
    Next
    INDEX
    Explanations

    license, software, or feature type

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

    The neuron detects structural block‐opening tokens in code or math (e.g. “begin,” “cases,” “{”).

    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
    ಿಯ
    -0.87
     Uch
    -0.81
    oscopic
    -0.76
    ●
    -0.74
    esehen
    -0.73
    Precision
    -0.73
     case
    -0.72
    setMap
    -0.72
    KB
    -0.69
     .'
    -0.68
    POSITIVE LOGITS
    ⇉
    0.76
    ᛚ
    0.73
     harbor
    0.73
     Anyways
    0.69
     subclasses
    0.67
     pasaba
    0.67
     fièvre
    0.66
     menar
    0.66
    HARR
    0.65
    asztok
    0.64
    Activations Density 0.056%

    No Known Activations