© 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. 71282
    Prev
    Next
    INDEX
    Explanations

    below benchmark, lower than average

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

    conceptual physics

    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
    改變
    0.48
     compensate
    0.47
     ngoại
    0.45
     trenut
    0.44
     تغییر
    0.43
    <0x93>
    0.43
    ージュ
    0.43
     museo
    0.43
     documenti
    0.41
    t
    0.41
    POSITIVE LOGITS
     Проци
    0.46
     mindfulness
    0.46
     ALL
    0.44
    falls
    0.44
     fascia
    0.44
    蜢
    0.43
    ফের
    0.42
     meditative
    0.42
     fantástico
    0.41
     Mindfulness
    0.41
    Activations Density 0.000%

    No Known Activations