© 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-262K
    7. 28618
    Prev
    Next
    INDEX
    Explanations

    specific details and complex concepts

    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_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
    то
    0.48
    included
    0.48
    DISPLAY
    0.48
    i
    0.46
    simple
    0.46
    точные
    0.45
    м
    0.45
    marginTop
    0.44
    тру
    0.44
    п
    0.43
    POSITIVE LOGITS
     اله
    0.54
     somos
    0.49
     ihn
    0.48
     koos
    0.46
     lutte
    0.45
    ewód
    0.45
     bieten
    0.44
     sekä
    0.44
     maakt
    0.43
     użytk
    0.43
    Activations Density 0.001%

    No Known Activations