© 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. 28091
    Prev
    Next
    INDEX
    Explanations

    planning, research, and reporting

    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
     emperor
    0.38
    裸
    0.37
    industry
    0.37
    реа
    0.37
     Vanity
    0.36
    etele
    0.35
     odgovor
    0.35
    marin
    0.34
    aqs
    0.34
    এক
    0.33
    POSITIVE LOGITS
     mengaj
    0.44
    計画
    0.43
     계획
    0.42
    義
    0.40
     reprodu
    0.39
     reproduced
    0.38
     revisar
    0.38
    警告
    0.38
     الاص
    0.38
    اج
    0.37
    Activations Density 0.005%

    No Known Activations