© 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. 80011
    Prev
    Next
    INDEX
    Explanations

    organization, sensor, miles

    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
    彼らは
    -1.48
     paroisse
    -1.38
    Whilst
    -1.31
     église
    -1.23
    最高の
    -1.19
     humild
    -1.16
    であり
    -1.16
    alians
    -1.16
    ！？
    -1.13
    Ouverture
    -1.13
    POSITIVE LOGITS
     you
    1.42
    ٨
    1.40
    ẵ
    1.40
     performing
    1.30
    Web
    1.13
    Save
    1.10
     ニュ
    1.09
     CHICKEN
    1.09
      
    1.08
     Федерации
    1.08
    Activations Density 0.014%

    No Known Activations