© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110670
    Prev
    Next
    INDEX
    Explanations

    org. , org= , org/

    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
    
    -2.73
    珰
    -2.69
    齪
    -2.61
    <bos>
    -2.59
     Japão
    -2.53
     reconoc
    -2.44
    畤
    -2.39
    蠊
    -2.38
    驺
    -2.36
    铊
    -2.34
    POSITIVE LOGITS
    —
    2.97
    At
    2.66
    As
    2.59
    k
    2.59
    To
    2.48
    ？
    2.41
    j
    2.36
     {
    2.36
    When
    2.33
    ere
    2.27
    Activations Density 0.008%

    No Known Activations