© 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. 58889
    Prev
    Next
    INDEX
    Explanations

    design and technical expertise

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

    names or actions preceding outcomes

    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
    adds
    0.58
    v
    0.57
    ma
    0.56
     Adding
    0.56
    but
    0.51
    न
    0.50
    ↵
    0.49
    ن
    0.49
    adding
    0.48
    kr
    0.48
    POSITIVE LOGITS
     transgress
    0.54
     బీ
    0.51
    獧
    0.49
     Regents
    0.48
     বাংলাকে
    0.48
     diferenças
    0.48
     профе
    0.47
    ImageBeforeText
    0.46
     turbulent
    0.46
     المتح
    0.45
    Activations Density 0.000%

    No Known Activations