© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11289
    Prev
    Next
    INDEX
    Explanations

    domain suffixes

    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_7_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
     ascertained
    2.82
     alamy
    2.65
    哧
    2.64
    specialchars
    2.63
     ruins
    2.62
    𝑀
    2.52
    んばんは
    2.48
    addNew
    2.48
    푞
    2.47
     worthless
    2.43
    POSITIVE LOGITS
    l
    2.76
    er
    2.45
    ان
    2.19
    چنین
    2.18
    ੀ
    2.17
    ا
    2.16
    an
    2.12
    i
    2.02
    นี่
    1.99
    y
    1.97
    Activations Density 0.099%

    No Known Activations