© 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. 87723
    Prev
    Next
    INDEX
    Explanations

    constantly filled

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

    block style, takes extra

    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
     تر
    0.49
     فار
    0.47
     bárm
    0.47
    挍
    0.46
     hemos
    0.45
     آپ
    0.45
     MPL
    0.45
     lick
    0.43
     af
    0.43
     آف
    0.43
    POSITIVE LOGITS
    ιά
    0.46
    兵庫
    0.43
    ச்சர்
    0.42
    \},\{
    0.42
    даг
    0.41
    夢
    0.41
    ﺲ
    0.41
    ecirc
    0.41
    使命
    0.40
    詳しい
    0.40
    Activations Density 0.000%

    No Known Activations