© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117832
    Prev
    Next
    INDEX
    Explanations

    mini, wheel, parker, community

    np_acts-logits-general · gemini-2.5-flash-lite

    pleasure from learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     воду
    0.50
     চরিত্রে
    0.49
     мм
    0.45
    তুই
    0.45
    Header
    0.44
     سعد
    0.44
    ☺️
    0.44
    にと
    0.43
     চরিত্রের
    0.43
     Highlight
    0.42
    POSITIVE LOGITS
    有
    0.53
     fatten
    0.52
    ด้
    0.51
    逓
    0.49
    عات
    0.48
     ench
    0.48
     technically
    0.47
     autonomic
    0.46
     calendário
    0.46
     extremities
    0.45
    Activations Density 0.000%

    No Known Activations