© 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. 117357
    Prev
    Next
    INDEX
    Explanations

    compensation previously

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

    directives, emulation, causation

    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
    웰
    0.45
     था
    0.43
    ＝
    0.42
    طان
    0.41
     countermeasures
    0.41
     ≈
    0.40
    종
    0.40
    ≒
    0.40
    ヴ
    0.39
     آن‌ها
    0.39
    POSITIVE LOGITS
     Rhythm
    0.47
     kuris
    0.45
    uirre
    0.44
    ريقه
    0.44
     Nomin
    0.43
    នូវ
    0.43
     زيد
    0.43
    {\|
    0.42
    shop
    0.41
     Trying
    0.41
    Activations Density 0.000%

    No Known Activations