© 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. 10-GEMMASCOPE-RES-131K
    7. 58137
    Prev
    Next
    INDEX
    Explanations

    expressing likes and dislikes

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    haviours
    -1.17
    tellen
    -1.16
    editing
    -1.14
    🎚
    -1.14
    aktionen
    -1.13
    Geschiedenis
    -1.13
    }])
    -1.12
    pygame
    -1.12
    Martes
    -1.12
    usions
    -1.11
    POSITIVE LOGITS
     that
    1.47
     each
    1.26
     your
    1.16
     gelernt
    1.16
     he
    1.14
    ,
    1.11
     qualquer
    1.10
     every
    1.09
     next
    1.05
     between
    1.04
    Activations Density 0.044%

    No Known Activations