© 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. 25073
    Prev
    Next
    INDEX
    Explanations

    what is left

    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
    thenburg
    -2.25
    derdag
    -2.23
    嫑
    -2.09
    linawan
    -2.02
    inerario
    -2.02
    gefügt
    -2.02
    และ
    -2.02
    .
    -1.98
    臜
    -1.97
     moniker
    -1.96
    POSITIVE LOGITS
     That
    2.50
     multitude
    2.34
     Numerous
    2.33
    ↵
    2.25
    Donativos
    2.13
    ’
    2.06
    ように
    2.05
     So
    2.02
     Generally
    2.02
     Not
    1.97
    Activations Density 0.009%

    No Known Activations