© 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. 68506
    Prev
    Next
    INDEX
    Explanations

    in or at

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

    court, battery, advance

    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
     धरो
    0.54
    廼
    0.53
    を備
    0.52
     可愛い
    0.51
    なんて
    0.51
     Datos
    0.50
     可愛
    0.50
    тового
    0.50
    這麼
    0.49
    ぶん
    0.49
    POSITIVE LOGITS
    The
    0.49
    In
    0.46
    绵
    0.44
    icen
    0.44
     Parkland
    0.44
    inz
    0.44
    :
    0.44
    eqn
    0.43
     hinge
    0.43
    Origin
    0.43
    Activations Density 0.001%

    No Known Activations