© 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. 249628
    Prev
    Next
    INDEX
    Explanations

    Red ST

    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
     Skor
    0.50
    你會
    0.48
     nein
    0.47
     Stones
    0.47
    LIED
    0.47
    бна
    0.47
    鎊
    0.47
    完善
    0.46
    <unused713>
    0.46
    मि
    0.46
    POSITIVE LOGITS
    atique
    0.49
     те
    0.47
     쭉
    0.47
    ungsseite
    0.44
    therm
    0.43
    aków
    0.43
     ஒ
    0.43
    回の
    0.43
     टेंपरेचर
    0.43
     therm
    0.42
    Activations Density 0.001%

    No Known Activations