© 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. 13444
    Prev
    Next
    INDEX
    Explanations

    JSDoc tags

    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
     others
    -1.19
     klima
    -1.11
     Ș
    -1.10
     usługi
    -1.08
    之色
    -1.07
    𝐆
    -1.04
     ?
    -1.03
     muziek
    -1.03
     silikon
    -1.02
     then
    -1.02
    POSITIVE LOGITS
     Allerdings
    1.21
    LOAT
    1.17
    vosti
    1.16
     Deshalb
    1.15
     cualquier
    1.13
    parece
    1.10
    nthetic
    1.08
     Trotzdem
    1.08
     acepción
    1.07
    Preparazione
    1.07
    Activations Density 0.001%

    No Known Activations