© 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. 26924
    Prev
    Next
    INDEX
    Explanations

    and great controversy

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

    digital natives

    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
     out
    0.50
    OP
    0.49
    RY
    0.48
     up
    0.48
    O
    0.48
    ROW
    0.47
    G
    0.47
    오
    0.47
    END
    0.45
     pouces
    0.44
    POSITIVE LOGITS
     क्योंकि
    0.51
     definitively
    0.49
     احتجاج
    0.48
     പ്രതിഷേധ
    0.47
     कारण
    0.47
     sincerity
    0.47
     अन्य
    0.46
     दुष्प्रभाव
    0.46
    存档备份
    0.46
    ۤ
    0.46
    Activations Density 0.000%

    No Known Activations