© 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. 238246
    Prev
    Next
    INDEX
    Explanations

    Refrigerator Repair

    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
    疙
    0.49
    羔
    0.48
    asas
    0.48
    清洗
    0.47
    캬
    0.47
    자가
    0.46
     அன்ன
    0.46
    igar
    0.46
    cones
    0.46
     ಅಂಶ
    0.45
    POSITIVE LOGITS
     Sén
    0.45
    ‵
    0.45
     développ
    0.44
     décès
    0.44
    න්ධ
    0.43
     philosophies
    0.43
     chrét
    0.42
     '-':
    0.42
     recher
    0.42
     quotidien
    0.42
    Activations Density 0.001%

    No Known Activations