© 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. 110487
    Prev
    Next
    INDEX
    Explanations

    dressing rooms, vanities, makeup

    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
     Lob
    -0.81
     кухо
    -0.76
     hoodies
    -0.75
    たくない
    -0.73
     cafe
    -0.73
    lico
    -0.69
    textContent
    -0.68
     hoodie
    -0.67
     restaurant
    -0.66
     Hoodie
    -0.66
    POSITIVE LOGITS
     dressing
    2.63
     Dressing
    2.05
    dressing
    1.91
    Dressing
    1.88
     vanity
    1.76
     bou
    1.45
     dresser
    1.43
     makeup
    1.41
     Vanity
    1.41
     dressings
    1.24
    Activations Density 0.021%

    No Known Activations