© 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. 34-GEMMASCOPE-RES-131K
    7. 118709
    Prev
    Next
    INDEX
    Explanations

    Pasadena, Rose Bowl

    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_34/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
     mantel
    -0.73
     río
    -0.73
    likasi
    -0.72
     Geist
    -0.71
     dulce
    -0.71
     Acero
    -0.70
     pretext
    -0.69
    HomeAsUp
    -0.68
     barrera
    -0.68
     botella
    -0.67
    POSITIVE LOGITS
     Pasadena
    1.87
     Arroyo
    1.02
    Pas
    0.96
     Tournament
    0.92
    Tournament
    0.89
    adena
    0.88
     JPL
    0.78
    ibald
    0.75
    pas
    0.75
    Jet
    0.75
    Activations Density 0.030%

    No Known Activations