© 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. 96282
    Prev
    Next
    INDEX
    Explanations

    hotels in

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

    Titan, interference, Shutdown

    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
    heti
    0.48
     выполнять
    0.44
    olol
    0.44
     ডি
    0.44
    olik
    0.43
    texte
    0.42
    hect
    0.41
     //.
    0.41
    िसू
    0.40
    тыми
    0.40
    POSITIVE LOGITS
    この
    0.53
    ˖
    0.49
     cái
    0.47
     ciudades
    0.47
     ziemlich
    0.47
    吠
    0.47
    ロッパ
    0.47
    Когда
    0.46
    得
    0.45
     Когда
    0.44
    Activations Density 0.001%

    No Known Activations