© 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. 36157
    Prev
    Next
    INDEX
    Explanations

    help and discarded technology

    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
    PE
    0.46
     dyads
    0.44
     fugiat
    0.42
     wundersch
    0.42
    ಿಸಲಾಗಿದೆ
    0.42
     ಸ್ನೇ
    0.41
    fault
    0.40
    ﺷ
    0.40
     bisschen
    0.40
    Ag
    0.40
    POSITIVE LOGITS
    ،
    0.61
    :"
    0.50
     కరో
    0.46
     Workmen
    0.46
    ："
    0.46
    ，
    0.45
    ၊
    0.45
    :"",
    0.44
     auprès
    0.44
    ，「
    0.44
    Activations Density 0.013%

    No Known Activations