© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93636
    Prev
    Next
    INDEX
    Explanations

    Chelsea Film Theatre Flower

    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
    asant
    -0.82
     assurent
    -0.81
     Gentile
    -0.81
     cazul
    -0.77
    越好
    -0.74
     cinematography
    -0.73
    jerne
    -0.73
     solitaire
    -0.73
     leggera
    -0.72
     шаг
    -0.71
    POSITIVE LOGITS
     Clinton
    1.20
     Chelsea
    1.15
    Chelsea
    1.08
     Piers
    1.06
    Clinton
    0.90
     boots
    0.90
     Handler
    0.82
     конечно
    0.81
     variety
    0.81
     Pension
    0.80
    Activations Density 0.032%

    No Known Activations