© 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. 63629
    Prev
    Next
    INDEX
    Explanations

    your order or schedule

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

    explaining Ventura, tasks, calculation, essentially, squeeze, compatible, pipe, inhaled

    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
     Madeleine
    0.45
     ఎ
    0.44
    Анд
    0.44
     занима
    0.43
    आपको
    0.43
    涉及到
    0.42
     сили
    0.42
     aneurysm
    0.42
    聑
    0.42
    టువంటి
    0.42
    POSITIVE LOGITS
     rivol
    0.43
     sogno
    0.42
     թվ
    0.41
     skapa
    0.41
     vznik
    0.41
     odmah
    0.40
     valeur
    0.40
    CYCLE
    0.40
     Stunden
    0.40
     wohn
    0.39
    Activations Density 0.000%

    No Known Activations