© 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. 127877
    Prev
    Next
    INDEX
    Explanations

    javascript code and technical terms

    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
    </em>
    -1.09
    ież
    -1.09
     ideen
    -1.08
    의
    -1.05
     ottenere
    -1.02
    をかける
    -1.02
    pholes
    -1.02
     kooper
    -1.01
    响起
    -1.01
     ausgewä
    -1.01
    POSITIVE LOGITS
     of
    1.80
     naselje
    1.26
     what
    1.21
     it
    1.17
    ();
    1.07
    باشد
    1.05
    ộn
    1.05
     теперь
    1.03
     تاثیر
    1.02
    靥
    1.02
    Activations Density 0.000%

    No Known Activations