© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6526
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sampai
    0.48
     pints
    0.45
     barbit
    0.45
     š
    0.44
    ဟ
    0.44
     upon
    0.44
     بعد
    0.44
     até
    0.43
     уя
    0.43
     美
    0.42
    POSITIVE LOGITS
    placeholder
    0.49
    besie
    0.46
    $">
    0.42
     স্থগিত
    0.41
    壃
    0.40
    python
    0.40
    ="'
    0.39
    でしたが
    0.39
    නම්
    0.38
    resolved
    0.38
    Activations Density 0.114%

    No Known Activations