© 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. 89832
    Prev
    Next
    INDEX
    Explanations

    waiting list

    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
     presiden
    0.54
    ،
    0.53
     akik
    0.52
     referendum
    0.51
     parka
    0.51
     parku
    0.50
     deliver
    0.50
     across
    0.50
     littoral
    0.50
     buzzer
    0.49
    POSITIVE LOGITS
     செய்யப்பட்டு
    0.49
     ሂ
    0.46
    修正
    0.45
    !!!");
    0.45
     머
    0.45
     재생
    0.45
     ജോലി
    0.44
     입력
    0.44
    FindingsResponse
    0.43
    <unused164>
    0.43
    Activations Density 0.001%

    No Known Activations