© 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. 189899
    Prev
    Next
    INDEX
    Explanations

    signed copies

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

    seasoned avocado

    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
     cuisines
    0.45
     embezzlement
    0.45
    覬
    0.45
     allegation
    0.44
     botanique
    0.44
    kmale
    0.43
     morphogenesis
    0.42
     좋아하는
    0.42
     Dishes
    0.42
     allegations
    0.42
    POSITIVE LOGITS
    if
    0.47
    íst
    0.45
    fr
    0.45
    ™
    0.45
     port
    0.44
    W
    0.44
    at
    0.44
    🥶
    0.44
                   
    0.43
    core
    0.43
    Activations Density 0.000%

    No Known Activations