© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 107257
    Prev
    Next
    INDEX
    Explanations

    degrees, angles, units

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

    personal qualities and abstract concepts

    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
    ক
    0.54
     İzmir
    0.49
     Verenig
    0.48
    Oxford
    0.48
    Edinburgh
    0.47
    k
    0.47
    苏
    0.43
    Ви
    0.42
    一项
    0.42
    头
    0.42
    POSITIVE LOGITS
     tienes
    0.50
     mengerjakan
    0.50
     prosa
    0.50
     그다
    0.50
    ्रल
    0.49
     जानिए
    0.49
     ฝึก
    0.48
     humbly
    0.48
     namun
    0.48
     遊ん
    0.47
    Activations Density 0.000%

    No Known Activations