© 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. 132148
    Prev
    Next
    INDEX
    Explanations

    etching, English, optional, concert, returned, director

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

    eccentric, inclined, career, safeguard, dedicated

    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
    দ্বীপ
    0.45
    sim
    0.44
    re
    0.42
     te
    0.42
    ⁡
    0.42
    man
    0.41
     hu
    0.41
    সা
    0.41
     WATCH
    0.41
    WhatsApp
    0.41
    POSITIVE LOGITS
     brunâtre
    0.56
     xWidth
    0.56
     اضافی
    0.55
     Pltf
    0.53
    ژگی
    0.52
     oznacza
    0.52
     vérit
    0.52
     开始
    0.52
     ಈ
    0.52
     precepts
    0.52
    Activations Density 0.000%

    No Known Activations