© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200627
    Prev
    Next
    INDEX
    Explanations

    speed limit inserts

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

    list items or rules

    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
     Yes
    0.44
     withstand
    0.43
     notoriously
    0.43
     ကြ
    0.42
    ])));
    0.42
     remembering
    0.40
     grudge
    0.40
     rumoured
    0.40
    night
    0.39
     mischiev
    0.39
    POSITIVE LOGITS
    чених
    0.52
    စ္
    0.49
    ю
    0.48
    LEMENT
    0.47
    л
    0.47
     Вайлдберриз
    0.45
    с
    0.45
    нкт
    0.45
    единенных
    0.45
    ο
    0.45
    Activations Density 0.001%

    No Known Activations