© 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. 201796
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    High, Term, Authority, Safety, joy

    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
     energy
    0.50
    energy
    0.47
     traditional
    0.45
     think
    0.44
     major
    0.42
    。
    0.42
     tech
    0.42
     technology
    0.41
     national
    0.41
     dark
    0.41
    POSITIVE LOGITS
     заработной
    0.55
    愚
    0.53
     gấp
    0.49
     расти
    0.49
     необхідно
    0.48
     Ừ
    0.47
     angust
    0.47
    ----+---->
    0.47
    𒇉
    0.47
    蔬菜
    0.46
    Activations Density 0.000%

    No Known Activations