© 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. 117917
    Prev
    Next
    INDEX
    Explanations

    seasons and times of day

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

    The neuron fires on content words (open‐class words like 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
    Aacute
    -0.90
    HMAC
    -0.89
    wendungs
    -0.84
    fecture
    -0.83
    routine
    -0.83
     retourner
    -0.80
    KeyCode
    -0.78
    matem
    -0.77
    response
    -0.77
    üß
    -0.77
    POSITIVE LOGITS
     continuant
    0.90
     apparence
    0.85
     ushered
    0.83
     murano
    0.78
     barometer
    0.78
     впечатление
    0.77
     Continuation
    0.77
     registering
    0.76
     continued
    0.75
     aborto
    0.75
    Activations Density 0.011%

    No Known Activations