© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68448
    Prev
    Next
    INDEX
    Explanations

    importance on

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

    The neuron flags evaluative, opinionated content words—primarily adjectives and abstract nouns—that emphasize importance, quality, or atmosphere in a business‐oriented context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ignent
    -1.01
    ^^
    -0.99
     Rhod
    -0.98
     occas
    -0.97
     dată
    -0.96
    魄
    -0.96
    ofold
    -0.94
    closePath
    -0.94
    宜しくお願い
    -0.94
    保温
    -0.94
    POSITIVE LOGITS
    ↵
    1.03
    的情況
    1.01
     személy
    1.01
     саны
    0.97
     Раз
    0.96
    的感覺
    0.96
     szczegó
    0.94
     ilç
    0.93
    ,「
    0.93
     You
    0.92
    Activations Density 0.005%

    No Known Activations