© 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. 178276
    Prev
    Next
    INDEX
    Explanations

    bibliographic information

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

    Physical Obstructions

    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
    Negative Logits
     Betfair
    0.46
     vendas
    0.44
     conoscenza
    0.43
     estando
    0.43
     batt
    0.42
     gasto
    0.42
     Kumb
    0.42
     scad
    0.41
     katika
    0.41
    `),
    0.41
    POSITIVE LOGITS
    न्यूयॉर्क
    0.48
    Soil
    0.47
    है
    0.47
    Reasoner
    0.47
    Detail
    0.47
    Reason
    0.46
    Toronto
    0.46
    Bodies
    0.46
    Details
    0.46
    土壤
    0.45
    Activations Density 0.000%

    No Known Activations