© 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. 156118
    Prev
    Next
    INDEX
    Explanations

    WHAT IS

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

    Python function definitions

    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
    л
    0.53
    ти
    0.52
     ぐらい
    0.51
    ну
    0.50
    थ
    0.50
    ט
    0.50
    льным
    0.50
    т
    0.49
    ть
    0.49
    смо
    0.49
    POSITIVE LOGITS
     Restoration
    0.51
     Luxurious
    0.48
    interacting
    0.47
    connecting
    0.46
     Dal
    0.45
     Interactions
    0.45
     Poly
    0.44
    osilicate
    0.43
    connect
    0.43
    Selecting
    0.43
    Activations Density 0.001%

    No Known Activations