© 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. 144881
    Prev
    Next
    INDEX
    Explanations

    lecture on, salaries, programs

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

    route, termination, value, specific configuration

    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
    nivers
    0.51
     لفظ
    0.47
     segar
    0.46
    ner
    0.46
     Rudolph
    0.45
    ن
    0.45
     begins
    0.43
    iendo
    0.43
    Rich
    0.43
    *[
    0.43
    POSITIVE LOGITS
    設定
    0.46
     তারাই
    0.45
    事件
    0.44
    riteria
    0.44
     Salaries
    0.44
    щите
    0.43
     বেতন
    0.43
     তিনিই
    0.43
    カウント
    0.42
    ვენ
    0.42
    Activations Density 0.001%

    No Known Activations