© 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. 11225
    Prev
    Next
    INDEX
    Explanations

    a and the following word

    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
    e
    1.24
    an
    1.22
    a
    1.14
    itäten
    1.10
    rzeb
    1.10
    eyen
    1.08
    andır
    1.08
    oyen
    1.08
    gover
    1.07
    elser
    1.07
    POSITIVE LOGITS
    自体
    1.63
    FBSDKAccessToken
    1.62
     श
    1.61
     สุด
    1.57
    鷳
    1.54
    ៥
    1.53
     বৎ
    1.52
     Glastonbury
    1.51
    یس
    1.50
     امکان
    1.50
    Activations Density 0.000%

    No Known Activations