© 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. 144552
    Prev
    Next
    INDEX
    Explanations

    first Prospect, Symbian, Android platform, cotton industry

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

    maps and digital

    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
    *
    0.50
    ỗ
    0.47
    ành
    0.46
    ЕР
    0.46
    üşt
    0.45
    *%
    0.44
     খুঁজতে
    0.43
     взрослых
    0.43
     जवळपास
    0.41
     hugely
    0.41
    POSITIVE LOGITS
     Eintritt
    0.50
     représente
    0.46
    ၶ
    0.46
    ।)
    0.45
     Criticism
    0.45
    سع
    0.44
    کین
    0.44
    entric
    0.44
    udiant
    0.44
    ಕರ
    0.43
    Activations Density 0.001%

    No Known Activations