© 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. 94288
    Prev
    Next
    INDEX
    Explanations

    starting alone, optimization, sell, attention

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

    descriptions and specific actions

    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
     ،
    0.51
    ار
    0.47
    '،
    0.46
    ،
    0.46
    郦
    0.46
    Примеча
    0.46
    İstanbul
    0.45
    একটি
    0.45
    ؛
    0.45
    இந்த
    0.45
    POSITIVE LOGITS
     bonheur
    0.61
     eyeshadow
    0.50
     Vogue
    0.49
     destac
    0.48
     fiance
    0.48
     conjug
    0.48
     lover
    0.48
     dekor
    0.47
     screwdriver
    0.47
     retouch
    0.47
    Activations Density 0.002%

    No Known Activations