© 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. 182771
    Prev
    Next
    INDEX
    Explanations

    unmarked trailed

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

    refuses to build

    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
    他和
    0.46
    遊び
    0.45
    (
    0.44
    قاب
    0.44
    侣
    0.43
     simp
    0.43
    اگر
    0.43
    ೀಲ
    0.42
    h
    0.42
    θος
    0.42
    POSITIVE LOGITS
     مختلفة
    0.53
     отказыва
    0.52
     सेंटीमीटर
    0.51
    躹
    0.51
     моя
    0.50
     చేసిన
    0.48
     સૌ
    0.48
     അറിയി
    0.47
    𒊬
    0.47
     integro
    0.47
    Activations Density 0.000%

    No Known Activations