© 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. 27610
    Prev
    Next
    INDEX
    Explanations

    rejects, refuses, blocks, exceptions

    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
    저
    0.52
     metabolite
    0.48
    
    0.46
     Emotion
    0.45
    한
    0.44
    Prem
    0.43
     Prem
    0.42
     allerg
    0.41
     immun
    0.41
     Inuit
    0.41
    POSITIVE LOGITS
     fighters
    0.52
    ്
    0.52
    fighters
    0.52
    bollah
    0.48
     अपेक्षाकृत
    0.47
     SUBSTITUTE
    0.46
    ︱
    0.44
     EMPLOY
    0.44
    醬
    0.44
     गुप्त
    0.43
    Activations Density 0.019%

    No Known Activations