© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    equations and definitions

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

    mathematical formula definitions

    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
     चौधरी
    0.46
     സമയ
    0.43
    জনিত
    0.42
     ಮಧ್ಯ
    0.42
     सुल
    0.41
     جوړونک
    0.40
    遂
    0.39
    沏
    0.39
     নান
    0.38
     शकेल
    0.38
    POSITIVE LOGITS
     fenders
    0.52
     $=$
    0.51
     markers
    0.46
     visuals
    0.44
     increase
    0.43
     stands
    0.43
     final
    0.43
     metres
    0.42
     actuators
    0.42
     denotes
    0.42
    Activations Density 0.000%

    No Known Activations