© 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. 84579
    Prev
    Next
    INDEX
    Explanations

    data and configuration keys

    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
     health
    0.39
     age
    0.37
     ‘
    0.37
     giro
    0.36
     year
    0.35
     matters
    0.35
     result
    0.35
     ones
    0.35
     unfortunately
    0.34
     decedent
    0.34
    POSITIVE LOGITS
     Три
    0.43
     தாக்கு
    0.40
    UInteger
    0.40
    oders
    0.39
    ameras
    0.39
    DAAR
    0.38
    曆
    0.38
    忝
    0.38
    enko
    0.38
    ichage
    0.38
    Activations Density 0.010%

    No Known Activations