© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 7807
    Prev
    Next
    INDEX
    Explanations

    smile playing on his lips

    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
    o
    2.93
    ു
    2.76
    a
    2.73
    ing
    2.66
    e
    2.38
    rups
    2.36
    ei
    2.29
    يارات
    2.27
    িণ
    2.26
    ে
    2.18
    POSITIVE LOGITS
    िक्रमा
    4.27
    ंपरा
    3.13
    此同时
    3.08
     towar
    2.84
    ෑම
    2.78
    slaught
    2.68
    ৈতিক
    2.66
     behalf
    2.51
    ("/",
    2.47
    spunkt
    2.41
    Activations Density 0.517%

    No Known Activations