© 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. 122323
    Prev
    Next
    INDEX
    Explanations

    return postage and shipping

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

    know, again, etc

    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
     Berikut
    0.57
    Chúng
    0.50
     Bracelet
    0.50
    ोजन
    0.49
    Berikut
    0.49
    Bracelet
    0.49
    '$,
    0.47
     bracelet
    0.47
     bracelets
    0.46
     earrings
    0.46
    POSITIVE LOGITS
    himanyu
    0.53
    㐫
    0.45
    相邻
    0.43
    a
    0.43
     مطابق
    0.42
    jaw
    0.42
    aquin
    0.41
    word
    0.41
     idx
    0.41
     ইঙ্গ
    0.41
    Activations Density 0.000%

    No Known Activations