© 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. 173415
    Prev
    Next
    INDEX
    Explanations

    he was, she paused, signs had

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

    class public

    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
    8
    0.50
     doctor
    0.49
     lecturer
    0.49
     dokter
    0.48
     years
    0.48
     medis
    0.48
    9
    0.48
     revised
    0.47
     draft
    0.47
    7
    0.47
    POSITIVE LOGITS
     фунда
    0.56
    តម្លៃ
    0.53
     지나
    0.52
    طيني
    0.51
    reicher
    0.48
    ходил
    0.47
    lichen
    0.46
    блю
    0.46
    rische
    0.46
    𝗱
    0.46
    Activations Density 0.000%

    No Known Activations