© 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. 69939
    Prev
    Next
    INDEX
    Explanations

    advances, Senator, dressed, use

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

    under British, accesses a, spelled my

    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
     neler
    0.49
     examples
    0.48
     Examples
    0.46
     nurseries
    0.46
    ObjectMapper
    0.45
    Ū
    0.45
     are
    0.45
    RS
    0.44
     mesons
    0.44
     l
    0.43
    POSITIVE LOGITS
    改为
    0.52
    恶意
    0.52
    прода
    0.50
     deslig
    0.50
     berjudul
    0.49
     बदलकर
    0.49
     dispar
    0.49
     perjud
    0.48
     Sevilla
    0.47
    不喜欢
    0.46
    Activations Density 0.002%

    No Known Activations