© 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. 32723
    Prev
    Next
    INDEX
    Explanations

    learn more

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

    learning from data and 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
     மந்திர
    0.47
    旨
    0.45
     重
    0.42
    ArrayBox
    0.42
    CCO
    0.42
     ಕೇಂದ್ರ
    0.41
    ilin
    0.40
    centric
    0.39
    instead
    0.39
    랍니다
    0.39
    POSITIVE LOGITS
     обучения
    0.49
    车
    0.49
     appren
    0.49
     Học
    0.48
    สอน
    0.46
     vehículos
    0.45
     Tune
    0.45
     ning
    0.44
    𝐇
    0.43
    रोवर
    0.43
    Activations Density 0.003%

    No Known Activations