© 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. 153944
    Prev
    Next
    INDEX
    Explanations

    equipped workshop

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

    technical and academic concepts

    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
    天
    0.51
    ∖
    0.44
    月
    0.43
    Recorder
    0.43
     FileManager
    0.43
     યાદ
    0.42
    錄
    0.42
     bypassing
    0.41
    命中
    0.41
    符
    0.41
    POSITIVE LOGITS
     universitet
    0.57
     ünivers
    0.57
     нынеш
    0.55
     üç
    0.55
     escuelas
    0.54
     escolas
    0.52
     actualmente
    0.52
     laborator
    0.52
     civ
    0.52
     çalışan
    0.51
    Activations Density 0.000%

    No Known Activations