© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    cryptographic key

    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
    П
    1.21
     previstas
    1.11
     EventArgs
    1.10
     desde
    1.08
    们
    1.07
     Accueil
    1.06
    ందని
    1.06
     SqlCommand
    1.06
    އް
    1.05
    itting
    1.05
    POSITIVE LOGITS
    anego
    1.40
     zupeł
    1.33
    ુલ
    1.30
    وشی
    1.25
     konuda
    1.18
     qualche
    1.16
    canoe
    1.16
    spr
    1.14
    표
    1.14
    মাত্র
    1.14
    Activations Density 0.011%

    No Known Activations