© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    what explains concepts

    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
    Doors
    0.84
    He
    0.82
    ?
    0.81
    awas
    0.74
    Didn
    0.74
     اجرا
    0.74
    ?!?
    0.74
     siya
    0.73
    ؟
    0.72
    riko
    0.72
    POSITIVE LOGITS
     globalization
    0.90
     understanding
    0.85
     investing
    0.85
     making
    0.83
     سمجھتے
    0.82
     managers
    0.82
     verstehen
    0.81
    懂得
    0.81
     vectors
    0.79
     browsing
    0.79
    Activations Density 0.075%

    No Known Activations