© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7697
    Prev
    Next
    INDEX
    Explanations

    code block closers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    जीलैंड
    1.11
    getTransforms
    1.08
    жных
    1.04
     exclusivos
    1.04
     divaricatis
    1.02
    <unused1259>
    1.02
    निश्ड
    1.00
     स्थाई
    0.99
    楤
    0.99
     فونبٹ
    0.99
    POSITIVE LOGITS
    ".
    1.12
    "]
    1.04
    ."
    1.00
    "].
    0.99
    ..."
    0.97
    "
    0.96
    </b>
    0.92
     which
    0.91
    」
    0.91
    which
    0.89
    Activations Density 0.206%

    No Known Activations