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. 29-GEMMASCOPE-2-RES-262K
    4. 1039
    Prev
    Next
    INDEX
    Explanations

    beautiful, gorgeous, and stunning descriptions

    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_262k_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
    垡
    0.66
    fileupload
    0.66
    יית
    0.62
    чивать
    0.61
    mods
    0.61
    Consent
    0.58
    ährung
    0.58
    洊
    0.58
    Fundamentals
    0.58
     thePack
    0.58
    POSITIVE LOGITS
     beautiful
    5.11
    beautiful
    4.38
     Beautiful
    4.37
    Beautiful
    4.25
     gorgeous
    4.20
     beauty
    4.08
     BEAUT
    3.93
     아름
    3.70
     beautifully
    3.69
     stunning
    3.64
    Activations Density 0.547%

    No Known Activations