© 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. 18327
    Prev
    Next
    INDEX
    Explanations

    speaker followed by colon or says

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

    dialogue attribution from names

    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
    機能を
    0.52
     einen
    0.49
     "",
    0.46
    %，
    0.46
     '',
    0.44
    了一個
    0.44
    りと
    0.42
     binaries
    0.42
     batches
    0.41
     eine
    0.41
    POSITIVE LOGITS
    ：
    0.76
    ：「
    0.73
    ：“
    0.71
    :
    0.63
    *:
    0.63
    ፦
    0.63
     says
    0.61
     replied
    0.56
     বলেন
    0.56
     berkata
    0.56
    Activations Density 0.050%

    No Known Activations