© 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. 27353
    Prev
    Next
    INDEX
    Explanations

    Taylor and Francis

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

    Zachary Taylor or Taylor & Francis

    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
    ทธิ
    0.51
    的状态
    0.50
    냈
    0.49
     ایالات
    0.48
    ༢
    0.48
    ท
    0.47
    October
    0.46
    พิเศษ
    0.46
    었다
    0.46
    ╋
    0.46
    POSITIVE LOGITS
     I
    0.59
     TAC
    0.50
     SME
    0.49
     PTFE
    0.49
     TAS
    0.48
     tach
    0.47
     PSY
    0.47
     P
    0.47
     WILL
    0.47
     PIC
    0.47
    Activations Density 0.001%

    No Known Activations