© 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. 16681
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formal text

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

    tool

    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
    ียด
    0.48
    មុខ
    0.44
     تربيع
    0.44
     peças
    0.44
     seascape
    0.43
    Ạ
    0.43
    貓
    0.42
    餐廳
    0.42
     đô
    0.42
    DanhMucSP
    0.41
    POSITIVE LOGITS
    <h4>
    0.59
    <h3>
    0.56
    *
    0.54
    <sup>
    0.53
    <h5>
    0.52
    »
    0.48
    ">
    0.46
    "
    0.45
     Windows
    0.45
    ¹)
    0.45
    Activations Density 0.182%

    No Known Activations