© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11865
    Prev
    Next
    INDEX
    Explanations

    scripting code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Restriction
    0.37
    asInstanceOf
    0.37
    ون
    0.35
    垒
    0.35
    Vale
    0.35
    restriction
    0.34
     ժ
    0.34
    شي
    0.34
    stelling
    0.33
    Outlet
    0.33
    POSITIVE LOGITS
     Constants
    0.46
     -*-
    0.43
     hyperparameters
    0.43
     Neural
    0.42
     Variablen
    0.42
     ARIMA
    0.42
     Imports
    0.41
     constants
    0.41
     Python
    0.41
    📶
    0.41
    Activations Density 0.002%

    No Known Activations