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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26220
    Prev
    Next
    INDEX
    Explanations

    comment introduction

    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
    +='
    -1.30
    URDAY
    -1.25
     czerwca
    -1.22
     generate
    -1.20
     sierpnia
    -1.19
    欧盟
    -1.19
     time
    -1.17
     items
    -1.16
     build
    -1.16
     self
    -1.14
    POSITIVE LOGITS
    Seguir
    1.30
    autres
    1.20
     potrà
    1.20
    Want
    1.20
     faciliter
    1.16
    Comprar
    1.15
    Continuar
    1.14
     conosce
    1.12
     cinquième
    1.11
     accompagner
    1.10
    Activations Density 0.006%

    No Known Activations