© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4191
    Prev
    Next
    INDEX
    Explanations

    dark colors and attributes

    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
    PROT
    -0.92
    landi
    -0.88
    InputStream
    -0.81
     angelegt
    -0.80
    Alloc
    -0.80
    <0xE4>
    -0.80
     kän
    -0.79
    ʽ
    -0.79
    Hidden
    -0.79
     可愛
    -0.79
    POSITIVE LOGITS
     dark
    1.16
    dark
    1.03
     DARK
    0.97
     if
    0.89
     darker
    0.88
     which
    0.86
     Dark
    0.85
    indeer
    0.81
     focus
    0.80
     casos
    0.80
    Activations Density 0.002%

    No Known Activations