© 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. 34-GEMMASCOPE-RES-131K
    7. 62391
    Prev
    Next
    INDEX
    Explanations

    javascript function definitions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鼉
    -1.18
    pergillus
    -1.16
     సౌ
    -1.13
    ꯭
    -1.09
    ſten
    -1.05
    lifies
    -1.02
    Voltaje
    -1.02
     AtomicInteger
    -1.02
    伢
    -1.02
    鸰
    -1.00
    POSITIVE LOGITS
     (
    2.03
    (
    1.36
    <em>
    1.20
    </h2>
    1.18
    </h4>
    1.17
    </strong>
    1.10
    <i>
    1.09
    ()
    1.01
    」
    0.95
    </b>
    0.94
    Activations Density 0.006%

    No Known Activations