© 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. 148419
    Prev
    Next
    INDEX
    Explanations

    God, Lake, daughter, timer, error

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

    Asia, Persian, warmth, improvement

    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
    l
    0.54
     H
    0.51
     C
    0.49
     E
    0.48
     M
    0.47
     sock
    0.46
     n
    0.45
    )
    0.45
     B
    0.45
     A
    0.45
    POSITIVE LOGITS
    ურთ
    0.50
    aları
    0.49
    alarına
    0.48
    ቨ
    0.47
    ினார்கள்
    0.47
    瞽
    0.47
     Алексей
    0.47
    靼
    0.46
     ঘু
    0.46
    ourent
    0.46
    Activations Density 0.003%

    No Known Activations