© 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. 19837
    Prev
    Next
    INDEX
    Explanations

    you'll be

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

    refer to me as

    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
    ATING
    0.47
    determining
    0.47
    Ahora
    0.46
    ப்பதற்கு
    0.45
     referentes
    0.45
    OGRAF
    0.45
    ִ
    0.45
    新た
    0.45
    WHAT
    0.44
    樁
    0.44
    POSITIVE LOGITS
     мяг
    0.43
     Mosaic
    0.41
    люб
    0.41
     Ramp
    0.40
     Yarm
    0.40
     moul
    0.40
     Eros
    0.40
     Nai
    0.39
    柔软
    0.39
     (£
    0.39
    Activations Density 0.001%

    No Known Activations