© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73550
    Prev
    Next
    INDEX
    Explanations

    unless, until, without, if then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Transk
    -1.09
    ⇩
    -1.05
     sò
    -1.05
     Vind
    -0.95
     vento
    -0.95
     sè
    -0.94
     gallina
    -0.94
    áculos
    -0.93
     satel
    -0.92
     pausa
    -0.92
    POSITIVE LOGITS
    mathrm
    1.04
    continue
    1.02
     sienten
    0.97
     Temmuz
    0.96
     cannot
    0.96
    jaros
    0.94
     Şubat
    0.92
     inspiradoras
    0.90
    จะ
    0.90
    <td>
    0.90
    Activations Density 0.025%

    No Known Activations