© 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. 86969
    Prev
    Next
    INDEX
    Explanations

    problems and causes

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

    This neuron fires on open‐class (content) words—nouns, verbs, adjectives, etc.—rather than on function words or punctuation.

    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
    慫
    -0.83
     these
    -0.81
    اااا
    -0.75
    徬
    -0.72
    zeczy
    -0.72
    王爷
    -0.71
    擋
    -0.71
    涪
    -0.71
     gratification
    -0.71
    if
    -0.71
    POSITIVE LOGITS
     banal
    0.94
     frequent
    0.88
    appeared
    0.85
     infantil
    0.84
     partial
    0.84
     colossal
    0.84
     avalanche
    0.84
     "
    0.82
    шк
    0.82
    ksan
    0.81
    Activations Density 0.027%

    No Known Activations