© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106302
    Prev
    Next
    INDEX
    Explanations

    grass fed

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

    recommends or requires specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PayPal
    0.46
    OpenJDK
    0.44
    Payment
    0.43
     something
    0.42
     IRC
    0.41
     vertebral
    0.41
     amort
    0.41
    <
    0.41
     আসন
    0.40
    Refund
    0.40
    POSITIVE LOGITS
    хта
    0.52
    ksen
    0.50
    ِه
    0.50
    isyen
    0.47
    хар
    0.46
    zens
    0.45
    acios
    0.45
     ديال
    0.45
    㝒
    0.45
    igning
    0.44
    Activations Density 0.000%

    No Known Activations