© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    couldn't quite articulate

    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
    त
    1.84
    an
    1.70
    我对
    1.63
    inizi
    1.59
    ك
    1.53
    情况下
    1.51
    jük
    1.51
    arono
    1.51
    that
    1.51
     söyledi
    1.48
    POSITIVE LOGITS
    ypse
    1.79
    벤트
    1.62
    shmi
    1.42
    很大
    1.42
    uzie
    1.38
     menggel
    1.35
    ্স্ট
    1.35
    ዌ
    1.34
    uncie
    1.34
    angkat
    1.33
    Activations Density 0.004%

    No Known Activations