© 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. 42687
    Prev
    Next
    INDEX
    Explanations

    place names and specific terms

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

    code snippets and technical terms

    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
     forskjellige
    0.43
    ింది
    0.43
    是通过
    0.43
    ំហ
    0.42
     日
    0.41
    вање
    0.41
    ෝජ
    0.40
     दत्ता
    0.40
     లో
    0.40
     彩
    0.40
    POSITIVE LOGITS
    sphere
    0.53
    north
    0.51
    rack
    0.49
     رئیس
    0.47
    札幌
    0.47
    isph
    0.47
    domains
    0.47
    روی
    0.47
    Seattle
    0.46
    sqlalchemy
    0.46
    Activations Density 0.001%

    No Known Activations