© 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. 204824
    Prev
    Next
    INDEX
    Explanations

    lifecycle management

    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
    quartered
    0.41
     Eller
    0.40
    stven
    0.39
    闥
    0.39
    Counc
    0.39
    displayed
    0.39
     }()
    0.38
    wright
    0.38
    ಾರೆ
    0.38
    albeit
    0.38
    POSITIVE LOGITS
     impurity
    0.42
     terrain
    0.37
     depreciation
    0.36
     pó
    0.36
     거기
    0.36
    ┄
    0.36
     depletion
    0.35
    )^{-\
    0.35
     diminishing
    0.35
     diminishes
    0.34
    Activations Density 0.000%

    No Known Activations