© 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. 169001
    Prev
    Next
    INDEX
    Explanations

    learned, imagining, offered, Regex, IP

    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
    0.55
    0
    0.55
     siehe
    0.40
     Uma
    0.39
    1
    0.39
     Manga
    0.38
     Chúa
    0.38
     and
    0.37
     &
    0.37
     lumin
    0.37
    POSITIVE LOGITS
    VRDR
    0.50
     массы
    0.49
    इंटर
    0.47
     रकम
    0.47
     ин
    0.47
    ısını
    0.46
     aniversário
    0.46
    एससी
    0.45
    cevam
    0.45
     جیتنے
    0.45
    Activations Density 0.006%

    No Known Activations