Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8748
    Prev
    Next
    INDEX
    Explanations

    body size and fit

    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
     cristian
    -0.93
     guber
    -0.90
    lexikon
    -0.89
    統
    -0.83
    cetos
    -0.81
     compiti
    -0.81
    scheid
    -0.80
     balls
    -0.80
     thứ
    -0.79
    ómicas
    -0.79
    POSITIVE LOGITS
     petite
    2.16
     slender
    1.59
     slim
    1.50
     skinny
    1.43
     tall
    1.41
     petites
    1.39
    petite
    1.24
     average
    1.20
     taller
    1.16
    slim
    1.14
    Activations Density 0.034%

    No Known Activations