© 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. 99362
    Prev
    Next
    INDEX
    Explanations

    award certificate templates

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

    Calculate Euler's totient function

    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
    '
    0.54
    ſelf
    0.53
     модель
    0.50
    eni
    0.50
     држа
    0.48
    hình
    0.47
    Trap
    0.46
    ította
    0.46
    ЕНИ
    0.45
    عة
    0.45
    POSITIVE LOGITS
     contests
    0.50
     costumes
    0.50
    OWL
    0.48
     analogs
    0.47
    ⒋
    0.47
     ya
    0.45
     awali
    0.45
    吆
    0.44
     Oxygen
    0.44
     motility
    0.44
    Activations Density 0.001%

    No Known Activations