© 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. 53-GEMMASCOPE-2-RES-262K
    7. 4279
    Prev
    Next
    INDEX
    Explanations

    wobbly technique

    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_53_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
    yó
    0.46
    〇
    0.44
    ○
    0.42
     ○
    0.40
     눈
    0.40
     নেওয়া
    0.39
    ';
    0.39
    '],
    0.39
    ')],
    0.39
     아
    0.38
    POSITIVE LOGITS
     moreover
    0.72
     furthermore
    0.66
     unquestionably
    0.61
     youll
    0.59
     merely
    0.54
     yakni
    0.52
     conceivable
    0.51
     asimismo
    0.50
     basically
    0.50
    basically
    0.50
    Activations Density 0.002%

    No Known Activations