© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    stem cells

    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
     Чтобы
    1.31
     dumbbells
    1.27
    الد
    1.26
    бей
    1.23
    Sous
    1.22
     DeepCollection
    1.21
     mathrm
    1.20
    ？](
    1.20
    *}$
    1.18
     PartialEq
    1.18
    POSITIVE LOGITS
    t
    1.68
    recht
    1.59
    エスト
    1.55
    uette
    1.48
    淇
    1.44
    fledged
    1.44
    g
    1.44
    trou
    1.39
    hood
    1.38
    次
    1.38
    Activations Density 0.010%

    No Known Activations