© 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. 66650
    Prev
    Next
    INDEX
    Explanations

    code blocks and references

    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
     parachoque
    -1.77
    臜
    -1.55
    
    -1.52
    März
    -1.51
     kabát
    -1.49
    皤
    -1.47
    besondere
    -1.42
     véhic
    -1.40
    これ
    -1.39
    <bos>
    -1.38
    POSITIVE LOGITS
    </strong>
    1.64
    </h4>
    1.50
    '
    1.49
     after
    1.47
     will
    1.45
     taken
    1.44
     at
    1.42
     had
    1.40
     -
    1.37
     k
    1.35
    Activations Density 0.001%

    No Known Activations