© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104435
    Prev
    Next
    INDEX
    Explanations

    .then( or |>

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gouttes
    -1.20
     プル
    -1.16
     déchets
    -1.14
     groote
    -1.11
     Cristóbal
    -1.09
     chofe
    -1.06
     marte
    -1.04
     avancer
    -1.03
     首页
    -1.03
    
    -1.02
    POSITIVE LOGITS
     also
    1.37
     with
    1.31
     or
    1.24
     també
    1.24
    ><
    1.20
     different
    1.18
     what
    1.17
     aussi
    1.13
     ((
    1.09
     lavish
    1.06
    Activations Density 0.002%

    No Known Activations