© 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. 127720
    Prev
    Next
    INDEX
    Explanations

    Bible verses and references

    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
     gmina
    -1.22
     some
    -1.13
     which
    -1.01
    ÈNE
    -0.99
     many
    -0.99
    langsung
    -0.99
    لم
    -0.95
     Slovensku
    -0.93
    ంగా
    -0.93
     but
    -0.92
    POSITIVE LOGITS
    Zitat
    1.26
    わけではない
    1.16
     infatti
    1.08
     intensifies
    1.00
    尤其
    0.99
     précédent
    0.98
    ńcu
    0.98
    racycline
    0.98
     reveló
    0.98
    äum
    0.98
    Activations Density 0.014%

    No Known Activations