© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    waste disposal and remodeling projects

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

    input, definitely, recognize, declarations

    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
     شی
    0.52
    嶂
    0.47
     стратеги
    0.46
     үшін
    0.46
     وک
    0.46
    rior
    0.46
     نادر
    0.46
    juv
    0.45
     Egipto
    0.45
    antos
    0.44
    POSITIVE LOGITS
    勸
    0.47
     chronically
    0.44
     breaches
    0.44
    漩
    0.44
     chronology
    0.44
     chronicles
    0.43
    飯店
    0.43
    лів
    0.42
    危機
    0.42
    ଲେ
    0.42
    Activations Density 0.000%

    No Known Activations