© 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. 10857
    Prev
    Next
    INDEX
    Explanations

    peer to peer

    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
    en
    3.51
    u
    3.25
    quela
    2.88
    o
    2.86
    ش
    2.47
    uwa
    2.45
    eniz
    2.42
    am
    2.41
     swore
    2.35
    oja
    2.35
    POSITIVE LOGITS
    т
    2.54
     fondateur
    2.45
    тся
    2.37
     ihe
    2.36
     Laat
    2.33
    ней
    2.32
     tearing
    2.28
    પણે
    2.27
     түз
    2.21
     Есть
    2.20
    Activations Density 0.070%

    No Known Activations