© 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. 110788
    Prev
    Next
    INDEX
    Explanations

    not created equal

    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
    Fixed
    -0.85
     onLoad
    -0.84
     motoru
    -0.82
     domy
    -0.81
     drze
    -0.80
     autre
    -0.79
     kabát
    -0.78
     najm
    -0.77
     Conférence
    -0.77
     Bitmap
    -0.76
    POSITIVE LOGITS
     equal
    2.97
     created
    2.47
    equal
    2.38
     Equal
    2.20
    Equal
    2.03
     equality
    1.97
     Created
    1.87
    created
    1.81
    Created
    1.80
     equals
    1.79
    Activations Density 0.022%

    No Known Activations