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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38943
    Prev
    Next
    INDEX
    Explanations

    calculation, data, or biological terms

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

    elements or components that are part of a numerical sequence or mathematical expression.

    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_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
     when
    -0.93
     препарат
    -0.85
     plakat
    -0.85
    できなかった
    -0.85
     filmu
    -0.81
     rád
    -0.81
     often
    -0.80
     często
    -0.79
     дори
    -0.79
     Often
    -0.77
    POSITIVE LOGITS
    products
    1.01
    fee
    1.00
    used
    0.96
    nex
    0.96
    both
    0.95
    launch
    0.94
     enti
    0.94
    items
    0.93
    ETHOD
    0.93
    send
    0.92
    Activations Density 0.070%

    No Known Activations