© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10941
    Prev
    Next
    INDEX
    Explanations

    AI models via API

    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
     ظ
    1.25
     mentor
    1.15
     пы
    1.12
    SIBLE
    1.11
    ثیر
    1.11
     forestry
    1.10
     },{
    1.09
     э
    1.09
    irectional
    1.09
     arduous
    1.07
    POSITIVE LOGITS
    autoplay
    1.30
    re
    1.27
    াল
    1.23
    ان
    1.23
    ά
    1.20
    该
    1.16
    ‌లో
    1.15
    م
    1.15
    బీ
    1.13
    ح
    1.11
    Activations Density 0.000%

    No Known Activations