© 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. 10-GEMMASCOPE-RES-131K
    7. 129820
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     our
    -1.55
    嫱
    -1.48
    ativistic
    -1.48
     so
    -1.41
    鷓
    -1.37
     there
    -1.36
     others
    -1.27
     навіть
    -1.25
    𝓒
    -1.25
    畕
    -1.24
    POSITIVE LOGITS
     alebo
    1.37
     vandaag
    1.27
     dahin
    1.26
    ingale
    1.24
    atest
    1.23
     verke
    1.21
    llog
    1.20
     ję
    1.19
    ofday
    1.18
    最初から
    1.18
    Activations Density 0.044%

    No Known Activations