Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7538
    Prev
    Next
    INDEX
    Explanations

    society

    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
    ر
    2.19
    驒
    1.99
     deceiving
    1.74
     effectuées
    1.70
    férence
    1.68
    𝐚
    1.63
     tête
    1.63
    siniz
    1.63
    णिज्य
    1.60
    হ
    1.59
    POSITIVE LOGITS
    ות
    2.64
    м
    2.50
    י
    2.34
    ی
    2.33
    й
    2.23
     таки
    2.12
     textField
    2.11
    мся
    1.93
    ة
    1.93
    ి
    1.91
    Activations Density 0.065%

    No Known Activations