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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3301
    Prev
    Next
    INDEX
    Explanations

    places and their descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    icius
    0.83
    刓
    0.70
    紵
    0.67
    getPackage
    0.66
    ಿಸಲ
    0.64
    ousine
    0.64
    ratio
    0.63
    鹉
    0.63
    VERSION
    0.63
     दोष
    0.62
    POSITIVE LOGITS
     places
    3.21
     place
    3.07
     tempat
    3.04
    場所
    2.84
     nơi
    2.84
    places
    2.71
     lugar
    2.70
    Places
    2.69
     lugares
    2.64
     Places
    2.61
    Activations Density 0.716%

    No Known Activations