© 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. 115135
    Prev
    Next
    INDEX
    Explanations

    successful slalom

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

    running models on limited hardware

    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
    主席
    0.49
    然而
    0.47
    <0xAB>
    0.47
    詼
    0.45
    鞦
    0.44
    סי
    0.44
    督
    0.44
    垁
    0.44
    劊
    0.44
    用的
    0.43
    POSITIVE LOGITS
     ধন্যবাদ
    0.50
     optimist
    0.48
     keel
    0.47
     touch
    0.46
     ditch
    0.46
     along
    0.46
     bookmark
    0.43
     farthest
    0.43
    er
    0.43
     kpc
    0.43
    Activations Density 0.001%

    No Known Activations