© 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. 10-GEMMASCOPE-RES-131K
    4. 9886
    Prev
    Next
    INDEX
    Explanations

    qualities, states, and degrees

    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
    derdag
    -1.59
    を作成
    -1.52
     toiture
    -1.51
    følgelig
    -1.48
    谁
    -1.48
    </i>
    -1.47
     that
    -1.44
    "));
    
    -1.43
    aced
    -1.42
    voyez
    -1.42
    POSITIVE LOGITS
    ="
    1.69
     according
    1.60
     \
    1.55
     if
    1.47
     other
    1.46
     on
    1.45
    𝘀
    1.38
    8
    1.34
     altri
    1.34
    1
    1.34
    Activations Density 0.111%

    No Known Activations