© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    weeks

    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
    ان
    4.02
    ت
    3.76
    𝙮
    3.69
    ためには
    3.68
    ে
    3.67
    ुसार
    3.55
    ی
    3.47
    ிர்
    3.45
    𝙖
    3.41
    لل
    3.41
    POSITIVE LOGITS
    des
    3.29
    mente
    3.06
    gi
    2.90
    do
    2.87
    di
    2.87
    ども
    2.82
    da
    2.79
    de
    2.73
    dy
    2.66
    اً
    2.65
    Activations Density 0.268%

    No Known Activations