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. 17-GEMMASCOPE-2-RES-65K
    4. 2002
    Prev
    Next
    INDEX
    Explanations

    labels and punctuation

    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
     माध्यम
    1.63
    getRepository
    1.62
    ᶰ
    1.62
    특별시
    1.59
    as
    1.57
    бло
    1.54
    
    1.53
    ار
    1.52
    द
    1.51
    𝒟
    1.49
    POSITIVE LOGITS
    esque
    2.16
    eer
    2.02
    ة
    1.92
    اں
    1.84
    eers
    1.83
    e
    1.80
    ことができる
    1.75
    tte
    1.66
    ees
    1.64
    า
    1.62
    Activations Density 0.000%

    No Known Activations