© 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-16K
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    Stanford Encyclopedia of Philosophy, Studies, Perspectives

    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_16k_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
    ت
    1.57
    િ
    1.55
     proximité
    1.50
    𝐭
    1.50
    서
    1.49
    𝐢
    1.48
    fledged
    1.40
    ✓
    1.39
     наличи
    1.36
     rámci
    1.34
    POSITIVE LOGITS
     originalmente
    1.33
    al
    1.23
    াবাহ
    1.18
     laufen
    1.16
     rzeczy
    1.16
     jotka
    1.16
     گا۔
    1.13
     rev
    1.12
    {(
    1.12
     irre
    1.12
    Activations Density 0.028%

    No Known Activations