© 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. 110935
    Prev
    Next
    INDEX
    Explanations

    leaving cold water

    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
     ಸುರ
    0.46
    spannung
    0.44
    膵
    0.43
     bezpečnost
    0.42
    addAction
    0.41
    hepatic
    0.40
    肝
    0.40
    ബരി
    0.40
    禟
    0.39
    सुर
    0.39
    POSITIVE LOGITS
     DOA
    0.41
     intelligent
    0.40
     недалеко
    0.40
     Intelligent
    0.38
     palk
    0.38
    ^)
    0.37
     +
    0.36
     ausgel
    0.36
     translucent
    0.36
     instrument
    0.36
    Activations Density 0.002%

    No Known Activations