© 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. 43246
    Prev
    Next
    INDEX
    Explanations

    city names and associated teams

    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
     If
    -3.39
     The
    -2.98
     When
    -2.84
     But
    -2.81
     Если
    -2.80
     While
    -2.64
     And
    -2.58
     With
    -2.55
     Certainly
    -2.53
     Perhaps
    -2.39
    POSITIVE LOGITS
    s
    3.34
    蓐
    2.77
     邸
    2.63
    ꯵
    2.55
    艄
    2.53
    
    2.44
    ㆆ
    2.41
     enfance
    2.41
    圌
    2.39
    莛
    2.38
    Activations Density 0.003%

    No Known Activations