© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
     насле
    0.46
     שע
    0.41
    ency
    0.39
    サンプル
    0.39
     skele
    0.38
    Assembl
    0.37
     ਬ
    0.37
    Synchron
    0.37
    Accum
    0.37
    Aplic
    0.37
    POSITIVE LOGITS
     Imports
    0.51
     imports
    0.49
     Trading
    0.45
     '../
    0.45
     Internal
    0.45
     './
    0.45
     Import
    0.45
     ImportError
    0.44
     '../../../
    0.43
    imports
    0.43
    Activations Density 0.063%

    No Known Activations