© 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. 1407
    Prev
    Next
    INDEX
    Explanations

    requests for sexually explicit content and generates refusals based on safety and ethical guidelines.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    creators and professors

    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
     thym
    0.28
     turbulent
    0.26
     cannibal
    0.26
     its
    0.24
    Pixmap
    0.24
     animation
    0.24
     western
    0.24
     x
    0.24
     primitive
    0.23
     NodeJS
    0.23
    POSITIVE LOGITS
     quienes
    0.33
     quien
    0.31
    यों
    0.30
     setempat
    0.29
     tarafından
    0.28
     którzy
    0.28
     responsáveis
    0.28
     ktorí
    0.28
    වර
    0.27
     advisors
    0.27
    Activations Density 0.417%

    No Known Activations