© 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. 229244
    Prev
    Next
    INDEX
    Explanations

    therapy, refund, keep, industry, because, Instead

    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
     馬
    0.59
     أجل
    0.50
     里
    0.49
    hotel
    0.48
     優
    0.48
     on
    0.46
    most
    0.46
    祭り
    0.45
    that
    0.44
    號
    0.44
    POSITIVE LOGITS
     überras
    0.49
     kaliteli
    0.49
     enthous
    0.47
     экстре
    0.47
     petits
    0.47
     اچ
    0.45
     auch
    0.45
     aluminium
    0.45
    าวิ
    0.44
     başarılı
    0.44
    Activations Density 0.000%

    No Known Activations