© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    explaining purpose or definition

    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_22_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
    து
    1.05
    י
    1.03
    もしくは
    1.03
    র
    1.02
    ো
    1.00
    k
    0.99
    кий
    0.97
    または
    0.97
     例えば
    0.97
    ة
    0.97
    POSITIVE LOGITS
     equidistant
    1.28
     exquisitely
    1.26
     implantation
    1.22
     помнить
    1.22
     shrewd
    1.20
     phospho
    1.19
     firepower
    1.18
    dashed
    1.17
     diminishing
    1.16
     inextricably
    1.16
    Activations Density 0.039%

    No Known Activations