© 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. 63875
    Prev
    Next
    INDEX
    Explanations

    numbers followed by measurement units

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

    language features

    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
    ́s
    0.49
     فتح
    0.44
    ̌
    0.44
     як
    0.43
    ppling
    0.43
    beds
    0.42
    etos
    0.42
     Donc
    0.41
     Haem
    0.40
     swaying
    0.39
    POSITIVE LOGITS
    ৬৮
    0.54
     درصد
    0.53
    clientsdetails
    0.53
    lobster
    0.48
    网上
    0.46
    出版
    0.45
    诒
    0.45
    ເຄື່ອງ
    0.44
    ື່
    0.44
    |$.
    0.44
    Activations Density 0.000%

    No Known Activations