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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 61250
    Prev
    Next
    INDEX
    Explanations

    redesign your home

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

    Lava, ransom, punk

    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
    䀎
    0.57
     поклон
    0.53
     гром
    0.52
     дов
    0.51
     गायक
    0.48
     метра
    0.47
     гля
    0.47
     επίσης
    0.46
     тариф
    0.46
    vvvert
    0.46
    POSITIVE LOGITS
     was
    0.45
    ɪ
    0.45
    顶
    0.43
    न्देल
    0.42
     অস্বাভাবিক
    0.42
    森
    0.42
    的历史
    0.42
     CNRS
    0.42
    的对象
    0.41
    卒
    0.40
    Activations Density 0.000%

    No Known Activations