© 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. 44004
    Prev
    Next
    INDEX
    Explanations

    proximity of

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

    states, conditions, or transitions

    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
    꿰
    0.49
     реализова
    0.47
    ઐ
    0.46
    椇
    0.44
     реализу
    0.42
    Opt
    0.42
     транспорти
    0.42
     startGame
    0.41
    entu
    0.41
    實
    0.41
    POSITIVE LOGITS
     முன்னர்
    0.54
     primeiras
    0.46
    ವಾಗಿ
    0.46
     profane
    0.45
     ಯಾವುದ
    0.45
    ವಾಗಿರುತ್ತದೆ
    0.44
     insufficiency
    0.44
    <0xAB>
    0.44
    ishly
    0.43
     moral
    0.43
    Activations Density 0.000%

    No Known Activations