© 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. 26822
    Prev
    Next
    INDEX
    Explanations

    religious and business terms

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

    tuple, dictionaries, keys

    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
     രാഷ്ട്ര
    0.59
    ٽ
    0.58
    脱
    0.49
     پہن
    0.49
     パン
    0.48
    ಗೊಂಡ
    0.48
    句話
    0.47
    قل
    0.47
    ائل
    0.47
    吊
    0.47
    POSITIVE LOGITS
     subdivision
    0.50
    udier
    0.50
     duo
    0.47
    neis
    0.46
    ए
    0.46
     colours
    0.46
     facilite
    0.45
     championship
    0.44
     συν
    0.44
     divisor
    0.44
    Activations Density 0.000%

    No Known Activations