© 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. 27587
    Prev
    Next
    INDEX
    Explanations

    reporting reasons behind data

    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
     cloak
    0.48
    出了
    0.44
    Charm
    0.42
    Burg
    0.41
    俏
    0.41
     pessoais
    0.41
    Viki
    0.40
    的环境
    0.39
    离开了
    0.38
    Stuff
    0.38
    POSITIVE LOGITS
     ${\
    0.45
     elucid
    0.45
    optimized
    0.44
     summarizing
    0.44
    thebetterindia
    0.44
     системати
    0.43
     dataset
    0.42
     combinatorial
    0.42
    あり
    0.42
     quantitative
    0.42
    Activations Density 0.003%

    No Known Activations