© 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. 144788
    Prev
    Next
    INDEX
    Explanations

    death, crime, or accidents

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

    fine-tuned, create, sanitize, overwinter

    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
    st
    0.52
    n
    0.51
    e
    0.49
    );
    0.49
    )
    0.49
    )=
    0.48
    std
    0.48
    ds
    0.47
    ;
    0.47
    x
    0.47
    POSITIVE LOGITS
    沇
    0.54
     व्यापारी
    0.52
     muere
    0.48
     pouls
    0.47
    悼
    0.47
    وسیع
    0.46
     tomado
    0.46
    दर्शी
    0.46
     مرگ
    0.45
     हादसा
    0.45
    Activations Density 0.001%

    No Known Activations