© 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. 22307
    Prev
    Next
    INDEX
    Explanations

    speaker attribution

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

    names speaking or reporting

    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
     объяснить
    0.54
    认为
    0.51
     säger
    0.51
    感慨
    0.50
    侃
    0.50
     говорит
    0.50
     mówi
    0.50
    觉得自己
    0.49
     मानते
    0.49
     बताती
    0.49
    POSITIVE LOGITS
     consecutive
    0.47
     s
    0.46
     l
    0.46
     slabs
    0.46
     matrices
    0.46
     (=
    0.44
     large
    0.44
     st
    0.44
     i
    0.43
     oper
    0.43
    Activations Density 0.015%

    No Known Activations