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. 9-GEMMASCOPE-2-RES-262K
    4. 7447
    Prev
    Next
    INDEX
    Explanations

    emojis and emotions

    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_9_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
    ように
    1.06
    sequently
    1.05
    clide
    1.02
     heavily
    0.95
    관
    0.95
    ilities
    0.94
    꾀
    0.91
     κε
    0.91
    غال
    0.89
    ல்லாம்
    0.89
    POSITIVE LOGITS
     resta
    1.35
     funcionamento
    1.35
    tors
    1.33
    tır
    1.30
    이
    1.27
    teddy
    1.26
     establece
    1.25
    aço
    1.25
    தர்
    1.25
     trabal
    1.23
    Activations Density 0.001%

    No Known Activations