© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    list separators and items

    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
     and
    1.37
     for
    1.10
     or
    1.09
    и
    1.08
     ហើយ
    1.02
    ی
    1.02
     और
    1.00
     এবং
    0.99
    and
    0.98
     to
    0.97
    POSITIVE LOGITS
     dikdört
    1.14
    蓣
    1.12
     RMSE
    1.11
    ஔ
    1.09
     '/')
    1.07
     varía
    1.06
    wać
    1.05
    椹
    1.04
     capaces
    1.04
     nurture
    1.04
    Activations Density 0.276%

    No Known Activations