© 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. 4087
    Prev
    Next
    INDEX
    Explanations

    font style for code snippets

    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
    ाइवेट
    0.46
     DISTRICT
    0.42
     okun
    0.42
    VSLU
    0.41
    忌
    0.41
     résident
    0.40
     Parole
    0.40
     कंडिशनर
    0.40
    ቓ
    0.39
    પાસ
    0.39
    POSITIVE LOGITS
     Script
    0.45
     bold
    0.45
    Script
    0.44
     script
    0.44
     mathematicians
    0.43
     math
    0.43
    U
    0.43
    ﾕ
    0.43
    rsfs
    0.42
     normal
    0.40
    Activations Density 0.001%

    No Known Activations