© 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. 169516
    Prev
    Next
    INDEX
    Explanations

    body, community, urban, wheel, licensing

    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
    fram
    0.40
    ≣
    0.40
     veículos
    0.38
     véhicules
    0.38
     FutureWarning
    0.38
    socketState
    0.38
    dataframe
    0.37
     cufflinks
    0.37
     بهترین
    0.36
     ovales
    0.36
    POSITIVE LOGITS
    기는
    0.39
     homemade
    0.38
    藜
    0.37
     away
    0.37
    away
    0.36
     calculus
    0.36
    aways
    0.35
     bě
    0.35
     Daly
    0.35
    𝗌
    0.35
    Activations Density 0.000%

    No Known Activations