© 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. 40337
    Prev
    Next
    INDEX
    Explanations

    newmarketsadoptBrianassemblepersonalYes

    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
     retiro
    0.55
    '
    0.54
     retirada
    0.49
     condicion
    0.46
     Slovakia
    0.44
     thermonuclear
    0.44
    ita
    0.44
    بوون
    0.43
     خواهند
    0.43
     ký
    0.43
    POSITIVE LOGITS
    Writing
    0.48
    Greg
    0.48
    Supp
    0.42
     написано
    0.42
    輋
    0.42
    एक
    0.42
    屐
    0.42
    Browser
    0.41
    ግዳ
    0.41
    aggreg
    0.41
    Activations Density 0.018%

    No Known Activations