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. 29-GEMMASCOPE-2-RES-65K
    4. 41150
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    K
    1.17
    k
    1.08
    К
    1.04
     k
    1.02
    𝐊
    0.97
     K
    0.88
     कोर्स
    0.87
     Course
    0.86
     subject
    0.85
     course
    0.83
    POSITIVE LOGITS
    anis
    0.76
    attitude
    0.75
    asure
    0.71
    yny
    0.69
    vény
    0.68
    ناه
    0.67
    riever
    0.67
     VIDA
    0.67
    呿
    0.64
    ާއި
    0.64
    Activations Density 0.001%

    No Known Activations