© 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. 14566
    Prev
    Next
    INDEX
    Explanations

    EPS or eps followed by text

    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
    гун
    0.42
    boor
    0.42
    суз
    0.41
     IUnary
    0.41
    uigen
    0.41
     ､
    0.40
     NSUInteger
    0.40
    <unused1800>
    0.40
    紫
    0.39
    meln
    0.39
    POSITIVE LOGITS
     EPS
    0.63
    EPS
    0.60
    DPS
    0.50
     DPS
    0.47
     eps
    0.46
     Eps
    0.44
     XPS
    0.43
     ups
    0.42
     esp
    0.41
     Ups
    0.41
    Activations Density 0.002%

    No Known Activations