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. 1980
    Prev
    Next
    INDEX
    Explanations

    practical advice and options

    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
     Standard
    0.83
     
    0.80
     Term
    0.69
     (
    0.68
     Data
    0.68
     Стро
    0.68
     New
    0.67
     Mark
    0.65
     John
    0.65
    ID
    0.64
    POSITIVE LOGITS
     espectacular
    1.23
    ísima
    1.21
     touristic
    1.16
    ísim
    1.15
     sensorial
    1.14
    cargar
    1.12
    🤛
    1.12
    pción
    1.11
    carrito
    1.10
    ítica
    1.08
    Activations Density 0.486%

    No Known Activations