© 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. 170103
    Prev
    Next
    INDEX
    Explanations

    legal, insured, and licensed

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

    represents a, apply civil

    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
     topics
    0.46
     angle
    0.43
    isms
    0.43
     addBook
    0.42
     handling
    0.42
     scrapping
    0.42
    тный
    0.41
    標
    0.40
     altern
    0.39
     unsafe
    0.39
    POSITIVE LOGITS
     বাট
    0.49
     déco
    0.49
    society
    0.49
    species
    0.48
     jár
    0.48
    special
    0.47
    swarm
    0.47
    sab
    0.46
    district
    0.46
    swith
    0.46
    Activations Density 0.002%

    No Known Activations