© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55093
    Prev
    Next
    INDEX
    Explanations

    baking soda, skin, cats

    np_acts-logits-general · gemini-2.5-flash-lite

    Python, aliens, dual, Supreme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     බ
    0.51
     sightings
    0.50
    실
    0.49
    pośred
    0.48
     மணிய
    0.48
    żenia
    0.46
    카
    0.46
    ്യ
    0.46
     기록
    0.46
     direitos
    0.46
    POSITIVE LOGITS
     داریم
    0.48
    区域
    0.46
    同时
    0.45
     Scienze
    0.45
    Fo
    0.43
    冷凍
    0.43
    热
    0.43
    随着
    0.43
    相比
    0.42
    RestorePolicy
    0.42
    Activations Density 0.000%

    No Known Activations