© 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. 42063
    Prev
    Next
    INDEX
    Explanations

    you to

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

    Ruby shot

    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
    י
    0.56
    ﻚ
    0.50
    You
    0.50
    דות
    0.48
    他們
    0.48
    ICreate
    0.48
    他們的
    0.47
    他们
    0.47
    ﻞ
    0.47
    มอ
    0.46
    POSITIVE LOGITS
     hermana
    0.48
     passages
    0.46
    
    0.44
    á
    0.43
     circulación
    0.43
     irmã
    0.42
     ór
    0.41
    is
    0.40
    ándolo
    0.40
    になりました
    0.40
    Activations Density 0.000%

    No Known Activations