© 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. 70575
    Prev
    Next
    INDEX
    Explanations

    opera singing

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

    opera and singing

    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
     thermometers
    0.47
     ಕೇಂದ್ರ
    0.45
     антен
    0.44
     température
    0.44
     акаде
    0.44
    <unused66>
    0.43
     पॉइंट
    0.43
     কম্পিউটার
    0.43
     dialing
    0.42
    휋
    0.42
    POSITIVE LOGITS
     opera
    0.74
    Opera
    0.73
     Opera
    0.66
    opera
    0.64
     operas
    0.64
     sung
    0.58
     singers
    0.55
     singing
    0.54
    唱
    0.52
    歌
    0.51
    Activations Density 0.058%

    No Known Activations