Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12463
    Prev
    Next
    INDEX
    Explanations

    people and their roles

    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_16k_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
     athletes
    0.46
     operating
    0.43
     colleges
    0.40
     object
    0.39
     avi
    0.39
     athlete
    0.38
    1
    0.38
     un
    0.38
     college
    0.38
     podendo
    0.37
    POSITIVE LOGITS
    Ᏺ
    0.55
     rectas
    0.55
    respuesta
    0.52
     respuestas
    0.52
    steuerung
    0.51
    뭘
    0.50
     mensajes
    0.50
     nossa
    0.49
    versorgung
    0.49
     tisu
    0.49
    Activations Density 0.001%

    No Known Activations