© 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. 6638
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning or definitions

    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
     preachers
    0.32
     florals
    0.30
    .​​
    0.30
    ᖕ
    0.30
     romances
    0.29
    रिमेंट
    0.29
    𒋼
    0.29
     appointees
    0.28
     gardeners
    0.28
    ErrorBoundary
    0.28
    POSITIVE LOGITS
     $\
    0.53
     $
    0.48
     $|
    0.42
     P
    0.40
     δ
    0.39
     consider
    0.38
    0.38
     Assume
    0.37
     we
    0.37
     Let
    0.37
    Activations Density 0.100%

    No Known Activations