© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23557
    Prev
    Next
    INDEX
    Explanations

    code return values and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ((
    0.31
     isinstance
    0.30
    n
    0.30
    s
    0.30
    m
    0.30
    type
    0.30
    decode
    0.30
    new
    0.29
    np
    0.29
    parseInt
    0.29
    POSITIVE LOGITS
    蛩
    0.29
    >∕
    0.29
    Roasted
    0.28
    Rustic
    0.27
     varicose
    0.27
    queous
    0.27
    ORIA
    0.27
     lésions
    0.26
     लक्षण
    0.25
    स्तिष्क
    0.25
    Activations Density 0.022%

    No Known Activations