© 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. 88758
    Prev
    Next
    INDEX
    Explanations

    damages

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

    options and possibilities

    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
    أ
    0.49
    wait
    0.49
    瓈
    0.47
    </h3>
    0.47
    all
    0.46
    ää
    0.45
    آ
    0.45
    her
    0.45
    the
    0.45
    thats
    0.44
    POSITIVE LOGITS
     różne
    0.52
     blanchâtre
    0.52
     ángulo
    0.49
     chcesz
    0.47
    бля
    0.47
    ພວກເຮົາ
    0.47
    FOLDER
    0.47
    ,/*
    0.46
    िस्तान
    0.46
    гляда
    0.46
    Activations Density 0.000%

    No Known Activations