© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123773
    Prev
    Next
    INDEX
    Explanations

    technical elements and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тельной
    0.39
    ise
    0.38
    oring
    0.37
     एकूण
    0.37
    㓡
    0.36
    ApiKey
    0.35
     измере
    0.33
    йки
    0.33
    ॉरिटी
    0.33
    distinct
    0.32
    POSITIVE LOGITS
     ọ
    0.51
     escribir
    0.50
     pruebas
    0.49
     poes
    0.48
     nettoy
    0.48
     componentes
    0.46
     propried
    0.46
     saludar
    0.46
     libros
    0.45
     dioses
    0.45
    Activations Density 0.012%

    No Known Activations