© 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. 64458
    Prev
    Next
    INDEX
    Explanations

    hours, time, serving

    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
    Negative Logits
    qxd
    -0.96
     könne
    -0.94
    <td>
    -0.92
    ޤ
    -0.91
    kswagen
    -0.89
    calciatore
    -0.89
    ijnlijk
    -0.88
    极了
    -0.88
    GEBRA
    -0.88
     from
    -0.87
    POSITIVE LOGITS
     staff
    1.01
    Mejor
    0.97
     maternidade
    0.92
     correto
    0.91
     MEJOR
    0.89
     aparência
    0.88
    ästi
    0.87
    sper
    0.87
    koła
    0.87
     cues
    0.86
    Activations Density 0.031%

    No Known Activations