© 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. 196493
    Prev
    Next
    INDEX
    Explanations

    shimmery shadow

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

    alternative explanations or scientific concepts

    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
     jari
    0.57
     systematics
    0.52
     Talking
    0.49
    𝗷
    0.47
     Gov
    0.46
     CASA
    0.45
    鏗
    0.45
     morti
    0.44
    J
    0.44
    リーダー
    0.43
    POSITIVE LOGITS
    xl
    0.50
    pping
    0.47
    rends
    0.47
    supp
    0.46
    etr
    0.46
    slu
    0.46
    ep
    0.45
     সঙ্গীত
    0.45
     האל
    0.45
     مشر
    0.44
    Activations Density 0.000%

    No Known Activations