© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4681
    Prev
    Next
    INDEX
    Explanations

    Okay, let's

    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
    ệt
    2.33
    cznym
    2.29
    း
    2.14
    er
    2.06
     غ
    1.95
    ción
    1.93
    cznej
    1.92
     ارت
    1.89
    cies
    1.89
    šan
    1.88
    POSITIVE LOGITS
    CommonAncestor
    2.58
    ources
    2.39
     INTEREST
    2.23
    менование
    2.20
    ǘ
    2.12
    urion
    2.12
    которые
    2.11
     assume
    2.10
    runoff
    2.09
    ब्बत
    2.09
    Activations Density 0.313%

    No Known Activations