© 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. 139047
    Prev
    Next
    INDEX
    Explanations

    kings, elementary, food, water

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

    traditional however accurate

    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
     콜
    0.50
    t
    0.48
    oasis
    0.46
    rubber
    0.45
     Супер
    0.45
     ذریعے
    0.45
     headphone
    0.44
    column
    0.43
    에요
    0.43
     drug
    0.42
    POSITIVE LOGITS
    🌃
    0.47
    市長
    0.47
     acumul
    0.46
     карь
    0.44
    节奏
    0.44
    NV
    0.44
    前回
    0.43
    🌇
    0.43
     момент
    0.43
    モー
    0.42
    Activations Density 0.001%

    No Known Activations