© 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. 202208
    Prev
    Next
    INDEX
    Explanations

    serious negative outcomes

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

    zoning allows, licensing fees

    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
    珽
    0.51
    Các
    0.47
     υπάρχ
    0.46
    Không
    0.46
    各
    0.45
     EXISTING
    0.45
     প্রকল্প
    0.44
    үкт
    0.42
     দর্শকদের
    0.42
     dài
    0.42
    POSITIVE LOGITS
     morte
    0.54
    isone
    0.45
     obsol
    0.44
    inan
    0.43
     inescap
    0.43
     memoria
    0.42
     wartime
    0.42
     murderous
    0.42
    殞
    0.42
     refugee
    0.42
    Activations Density 0.002%

    No Known Activations