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. 7435
    Prev
    Next
    INDEX
    Explanations

    to management

    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
    s
    1.17
    ت
    1.16
    oe
    1.13
     RGB
    1.11
    مه
    1.08
    amd
    1.03
     ​​
    1.03
     NPR
    1.03
    تع
    1.01
     virtu
    1.01
    POSITIVE LOGITS
     colocadas
    1.41
     ईमित्र
    1.38
     établissements
    1.32
     topologically
    1.30
     hashTable
    1.29
     rivets
    1.28
     tional
    1.28
     schist
    1.28
    𒀸
    1.27
    acją
    1.26
    Activations Density 0.000%

    No Known Activations