© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12300
    Prev
    Next
    INDEX
    Explanations

    collocations or descriptive pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fram
    0.45
    ijo
    0.44
    elements
    0.44
    あ
    0.43
    à
    0.42
     precedents
    0.42
    ING
    0.42
    lug
    0.42
    ನ್
    0.41
    个
    0.41
    POSITIVE LOGITS
     الكسور
    0.46
    スの
    0.45
    gação
    0.44
    arians
    0.43
     sobą
    0.43
    രിക്കും
    0.43
    जिकल
    0.42
     Eve
    0.42
     свобод
    0.42
     願い
    0.42
    Activations Density 0.204%

    No Known Activations