© 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. 121803
    Prev
    Next
    INDEX
    Explanations

    instructions or explanations that follow "you"

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

    data transfer and analytics

    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
    ек
    0.52
    文書
    0.51
    管
    0.47
    黃
    0.44
    EDE
    0.43
    --,
    0.43
     Douglass
    0.42
    Му
    0.41
    とお
    0.41
    白
    0.41
    POSITIVE LOGITS
     thêm
    0.53
     প্রশংসা
    0.51
     приез
    0.49
     chấm
    0.49
     anuv
    0.47
     khen
    0.47
     আন্দ
    0.46
     xóa
    0.46
    studded
    0.46
     shelved
    0.46
    Activations Density 0.000%

    No Known Activations