© 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. 134876
    Prev
    Next
    INDEX
    Explanations

    describes things found

    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
    arom
    0.53
     নাম
    0.51
     ቅር
    0.50
     ಔಷಧ
    0.49
     ಸಂಗೀತ
    0.48
     री
    0.48
    <unused73>
    0.47
    fonts
    0.47
     งาน
    0.47
    ሪ
    0.47
    POSITIVE LOGITS
    し
    0.53
    Those
    0.49
    {'
    0.48
    ず
    0.47
    Ly
    0.45
    き
    0.45
    ZU
    0.43
    め
    0.43
     élytres
    0.42
    Man
    0.42
    Activations Density 0.000%

    No Known Activations