© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8541
    Prev
    Next
    INDEX
    Explanations

    red followed by specific words

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

    red color or red objects

    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_40_width_16k_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
    طب
    0.45
     Augusta
    0.45
     Augmented
    0.42
    య
    0.41
    viridis
    0.40
     Assembly
    0.40
     Arctic
    0.40
     Alpine
    0.40
     Disability
    0.40
    ುದು
    0.39
    POSITIVE LOGITS
     레드
    1.54
     red
    1.52
    红
    1.51
    Red
    1.50
     レッド
    1.46
    紅
    1.45
     Red
    1.45
    red
    1.42
     крас
    1.41
     красный
    1.41
    Activations Density 0.174%

    No Known Activations