© 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. 233331
    Prev
    Next
    INDEX
    Explanations

    you knew, understand the

    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
     Orta
    0.47
    ৌক
    0.44
    ak
    0.43
    的
    0.43
    ()}
    0.42
    using
    0.42
    ات
    0.41
     namen
    0.41
    의
    0.41
    டித்த
    0.41
    POSITIVE LOGITS
    творю
    0.46
    ủy
    0.44
    ^+,
    0.42
     บวก
    0.41
    เมตร
    0.41
     Strictly
    0.40
     तेजस्वी
    0.40
     เลือก
    0.40
     रास्ते
    0.40
     comentário
    0.40
    Activations Density 0.000%

    No Known Activations