© 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. 10-GEMMASCOPE-RES-131K
    7. 70725
    Prev
    Next
    INDEX
    Explanations

    born and son of

    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
    ">
    -1.44
     ろう
    -1.33
    !
    -1.30
    cún
    -1.27
    prender
    -1.25
     تصریح
    -1.24
    ﮭ
    -1.23
    orta
    -1.23
     particulières
    -1.23
    ꒪
    -1.22
    POSITIVE LOGITS
     of
    1.81
     देखा
    1.34
    "....
    1.28
     стрем
    1.27
    oniec
    1.26
    ‌هایی
    1.18
    شا
    1.18
    dersfield
    1.17
    Ƴ
    1.16
     while
    1.15
    Activations Density 0.040%

    No Known Activations