© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28824
    Prev
    Next
    INDEX
    Explanations

    presentation outlines

    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_262k_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
    й
    0.46
     version
    0.45
     advances
    0.45
     versions
    0.45
     comprehension
    0.45
    м
    0.45
     sitio
    0.44
     leaf
    0.43
    єї
    0.43
     deflect
    0.43
    POSITIVE LOGITS
    埸
    0.55
    萏
    0.48
    Memento
    0.47
     ሳይ
    0.47
     유럽
    0.46
    Dance
    0.46
    Comedy
    0.45
    チック
    0.45
    स्पून
    0.45
     feme
    0.45
    Activations Density 0.005%

    No Known Activations