© 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-16K
    7. 2639
    Prev
    Next
    INDEX
    Explanations

    Okay, let's craft

    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_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
     Strict
    0.79
    сна
    0.78
     品
    0.78
     Commander
    0.75
    পট
    0.74
     rätt
    0.73
    geg
    0.73
     Commanders
    0.71
    зак
    0.71
    感情
    0.70
    POSITIVE LOGITS
    </body>
    0.90
    <h1>
    0.90
     नाही
    0.85
    UPLOAD
    0.83
    oubt
    0.83
    不可能
    0.82
    
    0.82
    bankruptcy
    0.80
     univerz
    0.80
    |_
    0.80
    Activations Density 0.195%

    No Known Activations