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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1814
    Prev
    Next
    INDEX
    Explanations

    the, comparative modifiers

    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_17_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
    ر
    0.75
    耂
    0.72
     riport
    0.70
     inclusions
    0.68
    ৯
    0.68
    spaper
    0.68
    ন্যাশনাল
    0.67
     confronti
    0.67
     vuông
    0.66
    <unused57>
    0.66
    POSITIVE LOGITS
    get
    0.71
     way
    0.69
    more
    0.67
    o
    0.65
    way
    0.64
    你会
    0.64
    tm
    0.63
    time
    0.62
    lm
    0.62
    Algun
    0.61
    Activations Density 0.190%

    No Known Activations