© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    / and @ symbols

    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
     (**
    0.82
     만들기
    0.82
    <0xD5>
    0.80
     자료
    0.80
     stimuli
    0.80
     workload
    0.78
     incision
    0.78
     scaffolding
    0.78
     LiDAR
    0.77
     occurrences
    0.77
    POSITIVE LOGITS
    Alex
    1.07
    John
    1.06
    J
    1.01
    K
    1.01
    D
    0.97
    j
    0.97
    S
    0.96
    Paul
    0.96
    El
    0.96
    Usuario
    0.95
    Activations Density 0.001%

    No Known Activations