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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10570
    Prev
    Next
    INDEX
    Explanations

    taunt, taut, Taunton

    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_10/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
     \
    -2.72
    </h3>
    -2.53
    ):
    -2.52
    {
    -2.44
    2
    -2.33
    i
    -2.28
    Zubereitung
    -2.16
    ve
    -2.11
    I
    -2.03
    <em>
    -2.02
    POSITIVE LOGITS
    齶
    2.78
    塒
    2.66
     resourceCulture
    2.45
    鮃
    2.39
    力
    2.38
    岨
    2.36
    
    2.30
    ܖ
    2.28
    
    2.25
    ᨒ
    2.23
    Activations Density 0.004%

    No Known Activations