© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7185
    Prev
    Next
    INDEX
    Explanations

    due to

    np_acts-logits-general · gemini-2.5-flash-lite

    giving reasons for refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    due
    0.44
     due
    0.42
     Due
    0.41
     Lint
    0.40
    ゃ
    0.39
    ھار
    0.38
    ⤴
    0.38
    Due
    0.38
    យក
    0.38
    Teddy
    0.37
    POSITIVE LOGITS
     malas
    0.40
     engagement
    0.40
     gourd
    0.39
    തിനുള്ള
    0.38
    ʊ
    0.38
    פון
    0.37
    군의
    0.37
    ïque
    0.37
    Engagement
    0.36
     stubbornly
    0.36
    Activations Density 0.002%

    No Known Activations