© 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. 127754
    Prev
    Next
    INDEX
    Explanations

    identifying and identity

    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
     вот
    -0.94
     prueba
    -0.94
     vivienda
    -0.94
     cidade
    -0.93
     настро
    -0.93
    ֹא
    -0.91
    ymi
    -0.91
     Beding
    -0.89
     buen
    -0.88
     faudrait
    -0.88
    POSITIVE LOGITS
     identification
    2.19
     identity
    1.61
    identification
    1.60
     identifying
    1.54
     identify
    1.51
     identities
    1.49
     identificar
    1.45
     identific
    1.38
     identifies
    1.38
     confirmation
    1.35
    Activations Density 0.065%

    No Known Activations