© 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. 260481
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     OFFER
    0.50
     люди
    0.50
    完全に
    0.49
    ាញ
    0.49
    чом
    0.49
    Чтобы
    0.48
     WHILE
    0.47
    А
    0.46
     Zil
    0.46
    サン
    0.45
    POSITIVE LOGITS
    ous
    0.52
    edt
    0.52
    anse
    0.52
    amas
    0.51
    oz
    0.51
    umas
    0.50
    og
    0.49
    ened
    0.49
    oa
    0.48
    aben
    0.48
    Activations Density 0.000%

    No Known Activations