© 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. 25081
    Prev
    Next
    INDEX
    Explanations

    enumerated lists and sequences

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

    list items or numbers

    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
     thương
    0.45
    欢
    0.44
    వేయ
    0.42
    getStudentNo
    0.42
    商品的
    0.42
    Gosudarstvennyj
    0.41
    歡
    0.41
    ोदय
    0.41
    "${
    0.40
     громадян
    0.40
    POSITIVE LOGITS
     частично
    0.49
     totaling
    0.48
     seterusnya
    0.48
     later
    0.47
     editions
    0.47
    0.46
     thirds
    0.45
     §§
    0.45
     two
    0.45
     thereafter
    0.44
    Activations Density 0.110%

    No Known Activations