© 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. 14351
    Prev
    Next
    INDEX
    Explanations

    splitting text and data

    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
    ه
    1.67
    NAL
    1.62
    aos
    1.60
     lưới
    1.60
     Bursa
    1.58
    मार
    1.58
    vem
    1.58
    a
    1.54
    Detail
    1.54
    aac
    1.51
    POSITIVE LOGITS
    ters
    1.87
    다면
    1.84
    ten
    1.75
    sky
    1.73
    тером
    1.65
    ্ৰ
    1.63
    ्स
    1.55
    tain
    1.54
    thren
    1.51
    tene
    1.50
    Activations Density 0.006%

    No Known Activations