© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    asking for context to refine

    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
     многочис
    0.48
     попыта
    0.43
     тщательно
    0.42
     もの
    0.41
    ٥
    0.41
    ➊
    0.40
     важней
    0.39
     innumerable
    0.39
     blatantly
    0.39
     comenzamos
    0.38
    POSITIVE LOGITS
     Warehouse
    0.48
     with
    0.45
     warehouse
    0.41
     Der
    0.38
     DA
    0.38
     Kudos
    0.38
     Biotech
    0.38
     G
    0.38
     DMS
    0.38
     Cord
    0.37
    Activations Density 0.072%

    No Known Activations