© 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. 57087
    Prev
    Next
    INDEX
    Explanations

    update or edit

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

    update and edit

    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
    </h3>
    0.54
     nuevas
    0.47
    </strong>
    0.46
     find
    0.46
     report
    0.44
     revers
    0.43
     novas
    0.43
     baru
    0.43
     नवीन
    0.42
    QP
    0.42
    POSITIVE LOGITS
     изменя
    0.60
    修改
    0.57
    Modify
    0.57
     modificare
    0.56
     моди
    0.55
    Modification
    0.54
    陴
    0.54
    بيه
    0.53
     modifié
    0.52
    Modified
    0.51
    Activations Density 0.004%

    No Known Activations