© 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. 74348
    Prev
    Next
    INDEX
    Explanations

    End of tour or program completion

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

    return 0;

    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
     आवाज
    0.51
     annum
    0.39
    ও
    0.39
    LineEdit
    0.38
     Orphans
    0.38
    兄
    0.38
    鰻
    0.38
     द्वि
    0.37
     Ấn
    0.37
    
    0.37
    POSITIVE LOGITS
     traduction
    0.43
    rien
    0.42
    نید
    0.41
    ↵↵
    0.40
     campagne
    0.40
     menjal
    0.40
     Barcel
    0.40
     fenomeno
    0.40
    ไปด้วย
    0.39
     batal
    0.39
    Activations Density 0.000%

    No Known Activations