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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 620
    Prev
    Next
    INDEX
    Explanations

    layout element or UI object

    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
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -1.63
     vanille
    -1.52
     mereka
    -1.38
     brune
    -1.36
     banane
    -1.33
     them
    -1.31
     fallecimiento
    -1.31
    壜
    -1.30
     décé
    -1.30
     démocratie
    -1.30
    POSITIVE LOGITS
    eronau
    1.30
     hicimos
    1.27
    脸色
    1.24
    vaila
    1.21
     kinda
    1.20
     چیز
    1.20
     onlyOwner
    1.20
    grees
    1.18
    isling
    1.16
    lossians
    1.15
    Activations Density 0.007%

    No Known Activations