© 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. 121480
    Prev
    Next
    INDEX
    Explanations

    dog, waiting, thankful, chain, money, neglect

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

    decisions ought to be made

    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
    戞
    0.54
    padă
    0.53
    蕩
    0.53
     রাস্ত
    0.50
    ხვ
    0.47
    ㄇ
    0.47
    嫋
    0.46
     ενός
    0.45
    ഷ്ട്ര
    0.45
     সড়ক
    0.45
    POSITIVE LOGITS
    <unused62>
    0.49
     theorems
    0.49
     פון
    0.49
    ments
    0.47
    ne
    0.45
    מ
    0.45
    me
    0.45
    has
    0.44
     titer
    0.44
    amen
    0.44
    Activations Density 0.001%

    No Known Activations