© 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. 19122
    Prev
    Next
    INDEX
    Explanations

    by followed by names

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

    by a legal

    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
    ㉖
    0.50
    InterfaceLine
    0.47
     anticipate
    0.46
    任意の
    0.46
     préférences
    0.44
     Mathematik
    0.43
    ೇಷ
    0.43
     entiende
    0.43
    PLICATION
    0.42
    Ň
    0.42
    POSITIVE LOGITS
     Marina
    0.48
    ose
    0.47
     Anna
    0.45
    ก่อน
    0.44
     I
    0.44
    เรีย
    0.44
     Mrs
    0.43
     A
    0.43
     Gerald
    0.43
    arest
    0.43
    Activations Density 0.000%

    No Known Activations