© 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. 136101
    Prev
    Next
    INDEX
    Explanations

    days of week and foreign languages

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

    specifics and categories

    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
    乚
    0.48
    nél
    0.48
     katk
    0.46
    ුරු
    0.44
    ()))
    0.44
    tos
    0.44
    都会
    0.43
    িনিয়র
    0.43
    呤
    0.43
    ຈາກ
    0.43
    POSITIVE LOGITS
     mercredi
    0.46
     sobren
    0.46
     thursday
    0.45
     mach
    0.43
     jueves
    0.43
     inconvenient
    0.43
    clidean
    0.42
     victoria
    0.42
     Secretaría
    0.41
    Accessed
    0.41
    Activations Density 0.001%

    No Known Activations