© 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. 237254
    Prev
    Next
    INDEX
    Explanations

    swap, change, operate, get, pack

    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
    ꯌ
    0.48
    🐕
    0.44
    oliko
    0.44
    ുട
    0.43
     geografia
    0.43
    㕕
    0.42
    ুক
    0.42
    अंत
    0.42
     বাঁধ
    0.42
    บริการ
    0.42
    POSITIVE LOGITS
    /
    0.52
     important
    0.51
     বয়স
    0.50
    (
    0.49
     inequities
    0.48
     irre
    0.48
    嚢
    0.47
    lder
    0.46
     figures
    0.46
    brev
    0.46
    Activations Density 0.000%

    No Known Activations