© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 604
    Prev
    Next
    INDEX
    Explanations

    question about relations

    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
     the
    1.45
     renowned
    1.14
    the
    1.13
    The
    1.11
     The
    1.10
     D
    1.09
     our
    1.06
     people
    1.06
     P
    1.03
     reliable
    1.02
    POSITIVE LOGITS
    ೇವಿನ
    1.36
     için
    1.36
     について
    1.25
     fyrir
    1.23
    Specs
    1.19
    ného
    1.18
     ಅನ್ನು
    1.17
     üçün
    1.15
    byId
    1.14
     รุ่น
    1.13
    Activations Density 6.275%

    No Known Activations