© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    top 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_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
    不良
    2.68
     dresser
    2.66
    𝚍
    2.63
    irst
    2.51
    href
    2.41
    weile
    2.29
     MEMBER
    2.25
    𝙳
    2.18
    maßen
    2.18
    льном
    2.17
    POSITIVE LOGITS
    ي
    3.37
    事人
    3.15
    鵑
    3.10
    وٹ
    2.96
    లు
    2.93
    Enumerable
    2.90
    िशनर
    2.86
    ástico
    2.76
    ForResult
    2.68
    maso
    2.65
    Activations Density 0.013%

    No Known Activations