© 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. 10012
    Prev
    Next
    INDEX
    Explanations

    idea of

    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
    د
    2.98
    ς
    2.94
    s
    2.79
    ﮄ
    2.65
    spect
    2.63
    дить
    2.61
    tin
    2.59
    sType
    2.54
    sic
    2.53
    𝒕
    2.53
    POSITIVE LOGITS
     adanya
    2.03
     stimulated
    1.99
    𝓮
    1.91
    的上
    1.84
     targ
    1.81
    jeet
    1.81
    াবহ
    1.80
    formatted
    1.79
    人的
    1.78
     '
    1.77
    Activations Density 0.222%

    No Known Activations