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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3291
    Prev
    Next
    INDEX
    Explanations

    number of items

    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_29_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
     toute
    0.64
    畩
    0.62
    リーブ
    0.62
    VITY
    0.62
    უკ
    0.61
    萬元
    0.61
    barung
    0.61
    抒
    0.61
    ത്തിയാ
    0.60
    洴
    0.59
    POSITIVE LOGITS
     number
    5.24
    number
    4.56
     número
    4.36
     Number
    4.29
    Number
    4.25
     aantal
    4.15
     Anzahl
    4.09
     تعداد
    3.99
     عدد
    3.87
     NUMBER
    3.80
    Activations Density 0.850%

    No Known Activations