© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    new class instantiation

    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
     其他
    2.75
     为了
    2.75
     嗯
    2.64
     一个
    2.62
     那
    2.59
     很
    2.57
     在
    2.56
     При
    2.54
     也
    2.52
     没有
    2.52
    POSITIVE LOGITS
    oot
    2.26
    uga
    2.17
    adi
    2.16
    ohl
    2.12
    bolo
    2.08
    lub
    2.05
    ito
    2.02
    iegel
    1.97
    すら
    1.96
    ule
    1.96
    Activations Density 0.008%

    No Known Activations