© 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. 183944
    Prev
    Next
    INDEX
    Explanations

    common contexts in descriptions

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

    spending a lot of time

    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
    В
    0.50
    <h3>
    0.47
    <h2>
    0.45
    З
    0.45
    <h1>
    0.43
    0.43
    อน
    0.42
    ynchronous
    0.41
    Ч
    0.41
    Big
    0.40
    POSITIVE LOGITS
     yǔ
    0.67
     wú
    0.64
     piernas
    0.56
     jīn
    0.53
     tienes
    0.52
     misdeme
    0.52
     じゃ
    0.52
     hü
    0.52
     prést
    0.52
     pued
    0.52
    Activations Density 0.000%

    No Known Activations