© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 65018
    Prev
    Next
    INDEX
    Explanations

    list containing structure

    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
     नौकर
    0.44
    ifizierung
    0.42
    ระบบ
    0.41
    стема
    0.41
    system
    0.41
    푞
    0.39
    ステム
    0.39
    keiten
    0.38
    mente
    0.38
    appelle
    0.38
    POSITIVE LOGITS
     I
    0.43
     decorar
    0.40
     animals
    0.39
     Beauty
    0.39
     
    0.38
     A
    0.38
     Politicians
    0.38
     biology
    0.38
     выбирать
    0.38
     to
    0.38
    Activations Density 0.001%

    No Known Activations