© 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. 242941
    Prev
    Next
    INDEX
    Explanations

    until well" or "until just"

    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
    าก
    0.54
    Dari
    0.51
    そらく
    0.49
    стан
    0.47
    ようです
    0.47
    സ
    0.47
    ังกฤษ
    0.45
    զ
    0.45
     ath
    0.45
    グラ
    0.45
    POSITIVE LOGITS
     Hamming
    0.49
     Pythagorean
    0.45
     ByteArray
    0.45
     Widgets
    0.44
    iotics
    0.44
     গুলি
    0.44
     তাঁরা
    0.43
     Shot
    0.43
     Depreciation
    0.43
     Decorative
    0.43
    Activations Density 0.000%

    No Known Activations