© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5701
    Prev
    Next
    INDEX
    Explanations

    leaving behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     마
    0.92
     우리
    0.79
     듣
    0.76
     카
    0.74
    วัสดี
    0.73
     porches
    0.72
     수
    0.72
     오늘의
    0.72
     our
    0.71
    江
    0.70
    POSITIVE LOGITS
    ($
    1.17
    ('@
    1.08
    ometry
    1.08
    ولو
    1.06
    䏲
    1.05
     وث
    1.04
     ($
    1.03
    ('_
    1.02
    بيق
    1.01
    ('#
    1.01
    Activations Density 0.013%

    No Known Activations