© 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. 245568
    Prev
    Next
    INDEX
    Explanations

    legal consultation, sound modalities, even if

    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
    chließlich
    0.51
     discredit
    0.50
    鼍
    0.49
    桥
    0.48
     compart
    0.47
    avut
    0.44
     çift
    0.44
    揽
    0.44
     criticise
    0.43
     გან
    0.42
    POSITIVE LOGITS
     BALANCE
    0.57
     Balance
    0.52
    WHY
    0.52
     nuestros
    0.50
     Nuestros
    0.50
     बटे
    0.50
     Monique
    0.49
     Buying
    0.48
     Buyers
    0.48
     Lorena
    0.47
    Activations Density 0.001%

    No Known Activations