© 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. 22-GEMMASCOPE-RES-131K
    4. 40230
    Prev
    Next
    INDEX
    Explanations

    gummy bears, court appeals

    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_22/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
     \
    -2.00
    it
    -1.79
     This
    -1.74
     desenli
    -1.70
     folgte
    -1.69
    si
    -1.65
     zewnętrzne
    -1.62
    us
    -1.61
     a
    -1.60
    ap
    -1.57
    POSITIVE LOGITS
    <bos>
    1.84
     будут
    1.69
    ↵↵
    1.59
     serán
    1.57
    鱨
    1.55
    because
    1.52
    かげ
    1.48
     будет
    1.46
     
    1.44
     ‐
    1.41
    Activations Density 0.001%

    No Known Activations