© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109698
    Prev
    Next
    INDEX
    Explanations

    beef growth estimates

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

    numerical values and statistical data in agricultural and scientific contexts.

    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
     Cricket
    -0.78
    PIT
    -0.75
    STP
    -0.75
    游戏亮点
    -0.73
    Investing
    -0.73
    Electrical
    -0.72
    clientWidth
    -0.72
    PV
    -0.72
    SUM
    -0.71
     tonos
    -0.71
    POSITIVE LOGITS
     forecast
    1.03
     estimates
    1.00
     forecasts
    0.93
     carry
    0.93
    SUPPLY
    0.90
     USDA
    0.88
     burdensome
    0.88
     analysts
    0.87
     supply
    0.84
     Supply
    0.84
    Activations Density 0.011%

    No Known Activations