© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    ACT, aggression, roster, Marcus

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

    office worker

    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
    לי
    0.45
    르
    0.43
    ז
    0.42
    פּ
    0.41
    Е
    0.41
    ૩
    0.41
    Hasil
    0.41
    יל
    0.41
    ૨
    0.40
    ג
    0.40
    POSITIVE LOGITS
    0.44
     and
    0.42
     cells
    0.37
    ).
    0.36
     buildings
    0.36
    ↵
    0.35
     structures
    0.35
     ii
    0.35
     macrom
    0.35
     cao
    0.34
    Activations Density 0.169%

    No Known Activations