© 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. 74177
    Prev
    Next
    INDEX
    Explanations

    food and items, body parts, business structures

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

    parts of speech, headings, or topics

    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
    provides
    0.39
     ಆರಂಭ
    0.39
     콘텐츠
    0.37
    ꒱
    0.37
    📥
    0.37
     projektu
    0.37
    新規
    0.36
    ⟤
    0.36
     Projekte
    0.36
    stven
    0.36
    POSITIVE LOGITS
    、
    0.44
     be
    0.39
    。
    0.39
     Toxicol
    0.38
     with
    0.38
     use
    0.38
     brag
    0.38
    !!!!!!!!
    0.37
     parallelogram
    0.37
    /
    0.37
    Activations Density 0.001%

    No Known Activations