© 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. 49987
    Prev
    Next
    INDEX
    Explanations

    collections

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

    The neuron flags content‐bearing words—especially nouns, verbs, adjectives, and proper names—while ignoring common function words.

    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
    択
    -0.81
     máximo
    -0.73
    crum
    -0.71
     журнал
    -0.71
    chèque
    -0.69
    んだよ
    -0.68
     informações
    -0.68
    kenal
    -0.68
    rø
    -0.67
    EmptyString
    -0.67
    POSITIVE LOGITS
     collection
    4.47
     collections
    3.70
    collection
    3.52
    Collection
    3.19
     Collection
    3.06
     COLLECTION
    2.81
    COLLECTION
    2.70
    collections
    2.63
     colección
    2.61
    コレクション
    2.36
    Activations Density 0.061%

    No Known Activations