© 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. 87701
    Prev
    Next
    INDEX
    Explanations

    educational contexts and definitions

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

    purely good or evil

    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
    匯
    0.56
    ாரா
    0.54
    ЛЯ
    0.51
    ந்தை
    0.47
    払い
    0.46
    ሪክ
    0.46
    न्दा
    0.46
    Ճ
    0.46
     viac
    0.46
    ണ്
    0.45
    POSITIVE LOGITS
    entine
    0.47
    icidal
    0.45
     göt
    0.45
     minions
    0.44
     sullen
    0.44
    stery
    0.44
     Groß
    0.44
     drag
    0.43
    issy
    0.43
    hte
    0.42
    Activations Density 0.001%

    No Known Activations