© 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. 21839
    Prev
    Next
    INDEX
    Explanations

    revision shall

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

    oyster and business

    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
     balconies
    0.36
    શે
    0.35
    ্ক
    0.35
     volley
    0.35
     disrespect
    0.35
     parmes
    0.35
     microSD
    0.35
    褙
    0.35
     vil
    0.34
     Football
    0.34
    POSITIVE LOGITS
    passenger
    0.42
    stedt
    0.40
    👨
    0.38
    detection
    0.38
    trag
    0.37
    숀
    0.36
    treatment
    0.36
     powertrain
    0.36
    jalan
    0.36
    brake
    0.35
    Activations Density 0.000%

    No Known Activations