© 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. 210755
    Prev
    Next
    INDEX
    Explanations

    information and privacy

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

    calendars and dates

    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
     strategy
    0.52
    ’
    0.50
     cre
    0.48
     didactic
    0.48
    '
    0.48
     predictable
    0.47
     says
    0.47
     reliable
    0.46
     potable
    0.46
     crew
    0.46
    POSITIVE LOGITS
    omitem
    0.56
    വിലെ
    0.53
     หนังสือ
    0.52
    ześnie
    0.51
     воздух
    0.51
    adinya
    0.49
    膘
    0.49
    สเตอร์
    0.48
    ⑤
    0.48
     อื่น
    0.47
    Activations Density 0.001%

    No Known Activations