© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20333
    Prev
    Next
    INDEX
    Explanations

    flow, speed, focused, geographic, temperatures, touch, signs

    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_31_width_65k_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
    5
    0.39
    6
    0.38
     bestät
    0.35
    4
    0.34
     Komponenten
    0.32
     después
    0.32
     delayed
    0.31
     slightly
    0.31
     ۴
    0.31
     réduite
    0.31
    POSITIVE LOGITS
    athons
    0.36
    собенно
    0.31
     oftentimes
    0.31
     ofthe
    0.31
    তাহ
    0.31
    。...
    0.31
    🌇
    0.31
     특히
    0.30
    밖에
    0.30
    ProtectedRoute
    0.30
    Activations Density 0.057%

    No Known Activations