© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70177
    Prev
    Next
    INDEX
    Explanations

    black and white films

    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
    FirebaseUser
    -0.86
     colourful
    -0.83
    ก่
    -0.81
     translucent
    -0.81
     颜色
    -0.80
    Blaze
    -0.79
    operazione
    -0.78
     Blaze
    -0.78
    williams
    -0.78
     coloré
    -0.75
    POSITIVE LOGITS
     black
    2.44
     черно
    2.16
     grayscale
    2.11
     monochrome
    2.03
    黑白
    2.03
     gray
    2.00
    black
    1.97
    gray
    1.91
     grey
    1.84
    흑
    1.75
    Activations Density 0.032%

    No Known Activations