© 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. 242460
    Prev
    Next
    INDEX
    Explanations

    ordering or offering specific items

    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
    திக
    0.48
    Manisha
    0.48
     Kishore
    0.47
     collateral
    0.45
    Chief
    0.44
    Coordinator
    0.44
    ők
    0.44
    ょ
    0.44
     Mith
    0.43
     Naga
    0.43
    POSITIVE LOGITS
     LETTERS
    0.52
     accep
    0.50
    世界上最大的
    0.50
    。”
    0.50
    ്ലാ
    0.50
     martes
    0.49
    дам
    0.49
    ！！！！
    0.48
    لاست
    0.48
     industrielle
    0.47
    Activations Density 0.000%

    No Known Activations