© 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. 123520
    Prev
    Next
    INDEX
    Explanations

    personal blogging

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

    Spark Origins, pixels, suspect something, Windows, Optimization

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Explicit
    0.47
     Random
    0.44
     θε
    0.44
     Mask
    0.42
    ↵
    0.42
     некоторые
    0.42
    吟
    0.41
     Camera
    0.41
    任意
    0.41
    仵
    0.41
    POSITIVE LOGITS
     już
    0.53
     undeniably
    0.48
     zaten
    0.47
     sekarang
    0.46
     bahut
    0.46
     połą
    0.46
     sudah
    0.46
     respectivement
    0.46
     rapide
    0.46
     dziś
    0.46
    Activations Density 0.000%

    No Known Activations