© 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. 111859
    Prev
    Next
    INDEX
    Explanations

    award amounts, information, or specific phrases

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

    striped tie

    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
     and
    0.50
     .
    0.45
     спокой
    0.45
     처
    0.44
     இதுவரை
    0.44
     much
    0.44
     progress
    0.43
    awks
    0.42
    .</
    0.42
     일반적으로
    0.42
    POSITIVE LOGITS
    تاة
    0.53
    غراف
    0.52
    ضة
    0.51
    гом
    0.50
    داث
    0.50
    ريخ
    0.49
    িবাস
    0.48
    ৫
    0.48
    Vall
    0.47
    ่ง
    0.46
    Activations Density 0.001%

    No Known Activations