© 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. 43326
    Prev
    Next
    INDEX
    Explanations

    date and numbers

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

    character development

    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
     juegan
    0.50
    RIM
    0.49
    স্ট
    0.48
    ש
    0.47
     jouent
    0.47
    ን
    0.47
    ar
    0.46
    Industry
    0.46
    Excluded
    0.46
     dividido
    0.46
    POSITIVE LOGITS
     来
    0.54
     weld
    0.52
     لے
    0.51
     ଦ
    0.48
     vaporization
    0.48
     來
    0.48
     یه
    0.47
     فرا
    0.47
     ބ
    0.47
    钡
    0.47
    Activations Density 0.000%

    No Known Activations