© 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. 43307
    Prev
    Next
    INDEX
    Explanations

    embryonic, photonic, gothic, symphonic

    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
    I
    -3.48
    *
    -3.19
    on
    -2.92
    >
    -2.83
    2
    -2.77
     
    -2.50
     And
    -2.47
     Of
    -2.44
    ?
    -2.41
    或者
    -2.36
    POSITIVE LOGITS
    깐
    3.09
    gliche
    2.69
    шении
    2.47
    蒟
    2.39
    ᥫ
    2.38
    émy
    2.38
    鸶
    2.38
    灩
    2.36
    𝄆
    2.36
    下一篇
    2.36
    Activations Density 0.038%

    No Known Activations