© 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. 34-GEMMASCOPE-RES-131K
    7. 49670
    Prev
    Next
    INDEX
    Explanations

    Folding@home distributed computing

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

    numbers and digits within text, particularly in dates and measurements.

    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
    Ordered
    -0.74
    ordered
    -0.72
    xor
    -0.71
    anchor
    -0.70
    story
    -0.70
    catch
    -0.68
     هست
    -0.68
    羅
    -0.68
    ,‎
    -0.68
    locale
    -0.67
    POSITIVE LOGITS
    Volunteer
    1.22
     Volunteer
    1.17
     seti
    1.09
     crun
    1.09
     Folding
    1.09
     volunteer
    1.05
    volunteer
    1.00
     volunteers
    0.93
    Folding
    0.93
    Distributed
    0.91
    Activations Density 0.033%

    No Known Activations