© 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. 36689
    Prev
    Next
    INDEX
    Explanations

    incentives and environment

    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
    ᱖
    0.54
     書い
    0.53
     insofar
    0.48
     nazionale
    0.46
    IBRARIES
    0.44
     lipase
    0.44
     congressional
    0.44
     prática
    0.44
     contato
    0.44
    сторія
    0.43
    POSITIVE LOGITS
     Emit
    0.52
     Expect
    0.50
     Stability
    0.50
    r
    0.49
     Jelly
    0.48
     Environment
    0.47
     Precision
    0.47
     Orange
    0.46
     Minimalism
    0.46
     Zebra
    0.46
    Activations Density 0.020%

    No Known Activations