© 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. 145327
    Prev
    Next
    INDEX
    Explanations

    deal, name, teams

    np_acts-logits-general · gemini-2.5-flash-lite

    describing emotional states or predictions

    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
     عند
    0.50
     vezes
    0.46
    開始
    0.44
    ता
    0.43
    㥆
    0.42
    often
    0.42
    лед
    0.41
     सत
    0.41
    обе
    0.41
    спорт
    0.40
    POSITIVE LOGITS
    1
    0.52
     cytosolic
    0.50
    2
    0.46
     marinated
    0.46
    Η
    0.45
     as
    0.45
     chưa
    0.44
     cytosol
    0.44
    r
    0.43
     Camila
    0.43
    Activations Density 0.001%

    No Known Activations