© 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. 25080
    Prev
    Next
    INDEX
    Explanations

    rug pull

    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
    re
    0.51
    ਸ
    0.50
    replacement
    0.44
    excerpt
    0.43
    fol
    0.43
     agenda
    0.43
    nueva
    0.43
    agn
    0.43
    о
    0.43
    s
    0.42
    POSITIVE LOGITS
     Underwood
    0.47
     WITH
    0.46
     sucesivamente
    0.46
     ϕ
    0.45
    ORICAL
    0.43
     Dough
    0.42
     पात्र
    0.42
    辇
    0.42
     ወቅት
    0.41
     प्रत्येक
    0.41
    Activations Density 0.003%

    No Known Activations