© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177287
    Prev
    Next
    INDEX
    Explanations

    felt covers

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

    notes after/about

    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
     Verma
    0.55
     tiny
    0.52
     Card
    0.50
    php
    0.50
    牌
    0.49
     f
    0.48
     Gi
    0.47
    K
    0.47
     small
    0.47
     Kristi
    0.47
    POSITIVE LOGITS
    ३
    0.62
    ו
    0.57
    荭
    0.52
     semelh
    0.51
     quantidades
    0.49
     parques
    0.49
    鹘
    0.48
    tevõ
    0.48
     inverno
    0.48
    溘
    0.48
    Activations Density 0.000%

    No Known Activations