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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 86274
    Prev
    Next
    INDEX
    Explanations

    words associated with snout

    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_16_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
    רות
    0.56
    6
    0.56
    сл
    0.55
    ای
    0.54
    رض
    0.54
    3
    0.54
     engl
    0.54
    د
    0.53
    سر
    0.52
    4
    0.52
    POSITIVE LOGITS
     legalization
    0.57
     traditional
    0.46
     southeastern
    0.44
     collaborator
    0.43
     chel
    0.43
    minic
    0.43
     limestone
    0.43
    ोरेशन
    0.43
     pioneering
    0.43
     blissful
    0.43
    Activations Density 0.001%

    No Known Activations