© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3581
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical figures

    np_acts-logits-general · gemini-2.5-flash-lite

    calculated numerical results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    abbanti
    0.48
    泷
    0.46
    饴
    0.45
    樯
    0.45
    Gosudarstvennyj
    0.44
    帏
    0.44
    屣
    0.43
    پيديا
    0.42
     మొక్క
    0.42
    狲
    0.42
    POSITIVE LOGITS
    0.64
     $
    0.50
    4
    0.48
    3
    0.47
    e
    0.47
    1
    0.47
    all
    0.46
    <0xE3>
    0.45
    www
    0.45
    i
    0.45
    Activations Density 0.033%

    No Known Activations