© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7688
    Prev
    Next
    INDEX
    Explanations

    ideas

    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_22_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
     ­
    0.93
    สมัย
    0.86
    ¤
    0.83
    สัก
    0.82
    ខ្ល
    0.81
    เน
    0.80
     วิธี
    0.80
     ช่วง
    0.79
    გრ
    0.78
     పరిస్థి
    0.78
    POSITIVE LOGITS
    .).
    2.32
    》。
    2.29
    )。
    2.27
    ）。
    2.13
    )।
    2.09
    .").
    2.07
    !).
    2.05
    .].
    2.03
    .");
    2.01
    ]。
    2.01
    Activations Density 0.508%

    No Known Activations