© 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. 48918
    Prev
    Next
    INDEX
    Explanations

    can affect

    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
     höhere
    0.51
    下の
    0.46
    崽
    0.45
    Ак
    0.43
     discret
    0.42
     sacer
    0.42
     illuminating
    0.41
     Oui
    0.41
    뜻
    0.41
    πα
    0.41
    POSITIVE LOGITS
    以免
    0.45
    usnya
    0.44
     செய்தி
    0.44
    ல்
    0.43
    ard
    0.42
    iy
    0.42
    ěz
    0.42
     безопасности
    0.42
     عنها
    0.41
     امنیت
    0.41
    Activations Density 0.003%

    No Known Activations