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. 9-GEMMASCOPE-2-RES-262K
    4. 7699
    Prev
    Next
    INDEX
    Explanations

    performances and presentations

    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
    us
    1.18
    на
    1.15
    INR
    1.13
    ѕ
    1.11
    들
    1.10
    रिया
    1.10
     čo
    1.10
     사항
    1.08
     الاج
    1.07
     nhắn
    1.07
    POSITIVE LOGITS
     linewidth
    1.33
    完毕
    1.28
    retval
    1.25
     concerts
    1.22
    OCO
    1.20
    phonon
    1.20
    ROI
    1.16
     Presentations
    1.15
    ম
    1.14
     webcast
    1.13
    Activations Density 0.109%

    No Known Activations