© 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. 10536
    Prev
    Next
    INDEX
    Explanations

    you want or have

    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
    o
    3.05
    ه
    3.03
    a
    2.89
    enia
    2.32
    gap
    2.29
    ి
    2.25
    도
    2.19
    일
    2.14
     o
    2.10
    𝙤
    2.05
    POSITIVE LOGITS
    <unused798>
    3.00
    үнд
    2.91
    鸯
    2.90
     অপরের
    2.86
     bpy
    2.79
    िकोण
    2.78
    পাশ
    2.76
    菻
    2.76
    飩
    2.76
     abertura
    2.75
    Activations Density 0.028%

    No Known Activations