© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110571
    Prev
    Next
    INDEX
    Explanations

    carbon storage

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

    citations, references, and parenthetical information in academic and technical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    其妙
    -0.74
     agonist
    -0.71
    sivity
    -0.71
    vio
    -0.70
    Doll
    -0.68
    target
    -0.68
     stormwater
    -0.68
    unts
    -0.67
    laden
    -0.66
     trivia
    -0.66
    POSITIVE LOGITS
    UNF
    0.79
     carbono
    0.78
     leakage
    0.76
     suppressed
    0.75
    监测
    0.75
    ḿ
    0.74
     Americano
    0.73
     Babi
    0.72
    dY
    0.72
     transparent
    0.71
    Activations Density 0.006%

    No Known Activations