© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8711
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    reserve and setting aside

    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_40_width_16k_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
     nami
    0.38
     Neil
    0.37
    pertino
    0.37
     Gareth
    0.37
     Charlene
    0.37
    ヤー
    0.37
    ('.');
    0.37
     угле
    0.36
     கவனம்
    0.36
    羰
    0.36
    POSITIVE LOGITS
     reserved
    2.28
     reserve
    2.25
    reserved
    2.17
    reserve
    2.16
     reserves
    2.08
     Reserved
    2.05
     reserv
    2.03
    Reserved
    2.02
     rezerv
    1.97
     reserva
    1.95
    Activations Density 0.117%

    No Known Activations