© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38613
    Prev
    Next
    INDEX
    Explanations

    code comments and syntax highlighting

    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
     type
    -1.43
     this
    -1.23
     husband
    -1.20
     school
    -1.17
     family
    -1.16
     groups
    -1.14
    ={()=>
    -1.13
     protein
    -1.10
     games
    -1.10
     when
    -1.10
    POSITIVE LOGITS
    Kanal
    1.27
    Voltaje
    1.27
     novità
    1.25
    Organisator
    1.23
    Angebot
    1.23
    Morfo
    1.23
    maior
    1.22
    Spann
    1.21
    توضیحات
    1.21
    Étape
    1.21
    Activations Density 0.001%

    No Known Activations