© 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. 56913
    Prev
    Next
    INDEX
    Explanations

    this firm refusal

    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
     practised
    0.47
    "+"|".
    0.46
     Vivekananda
    0.44
    owntown
    0.44
     morbidity
    0.43
     mysticism
    0.43
    igueur
    0.43
     Loyola
    0.43
    处罚
    0.43
     要求
    0.43
    POSITIVE LOGITS
     sys
    0.51
     suspensión
    0.46
     deň
    0.45
     alguns
    0.45
     presentación
    0.44
    도
    0.44
     liger
    0.44
     vertical
    0.43
    lx
    0.43
     gato
    0.43
    Activations Density 0.008%

    No Known Activations