© 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. 10-GEMMASCOPE-RES-131K
    7. 105261
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    indentation or whitespace at the beginning of lines in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron never fires on any of the shown tokens, i.e. it appears to be inactive (a “dead” neuron) in these examples.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    erializer
    -1.87
     -
    -1.77
    iços
    -1.68
     teniendo
    -1.66
     stolet
    -1.59
    namese
    -1.59
     Descripción
    -1.58
     PyLong
    -1.56
     cuyas
    -1.53
    薗
    -1.53
    POSITIVE LOGITS
    es
    1.98
    u
    1.74
    us
    1.68
    y
    1.65
    im
    1.65
    ir
    1.63
    他不
    1.60
    om
    1.59
     them
    1.56
    ).)
    1.56
    Activations Density 0.040%

    No Known Activations