© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    safety protocols and guidelines

    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
    法律
    0.44
    appreciated
    0.43
    awi
    0.43
    əsi
    0.42
    irst
    0.42
     hukuk
    0.39
    喈
    0.39
    éli
    0.38
     luật
    0.38
     Verenig
    0.38
    POSITIVE LOGITS
     جلوگیری
    0.54
     automatisch
    0.49
     avoiding
    0.49
     تلاش
    0.47
     avoidance
    0.46
    为了
    0.46
     efforts
    0.44
    䒺
    0.44
    為了
    0.44
     avoid
    0.44
    Activations Density 0.289%

    No Known Activations