© 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. 25111
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
     aparcamiento
    -1.14
     just
    -1.14
    莅
    -1.04
     any
    -1.02
    OptionsMenu
    -1.00
     horribly
    -1.00
    ôtel
    -0.98
    ֠
    -0.98
     but
    -0.97
    ########.
    -0.96
    POSITIVE LOGITS
     креди
    1.11
    leqslant
    1.09
     pivotal
    1.05
     experts
    1.04
     deems
    1.03
     eligible
    1.02
     rightful
    1.01
     nämlich
    1.00
     đà
    0.99
     nemlig
    0.98
    Activations Density 0.014%

    No Known Activations