© 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. 52691
    Prev
    Next
    INDEX
    Explanations

    you are right

    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
        
    0.48
    Removal
    0.46
    ொ
    0.46
    equivariant
    0.44
     subtiliter
    0.44
     Wrapper
    0.43
    اوی
    0.42
     traitements
    0.42
     Vast
    0.41
    Elem
    0.40
    POSITIVE LOGITS
     maximal
    0.48
     मैक्स
    0.47
     farmers
    0.44
     gouvernement
    0.44
    គួរ
    0.44
    犟
    0.44
     长
    0.43
     jub
    0.42
     Mayo
    0.42
     konkur
    0.42
    Activations Density 0.001%

    No Known Activations