© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102585
    Prev
    Next
    INDEX
    Explanations

    milliseconds, millipedes, miliary, millionaire, milligram

    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
    >
    -2.34
    瀦
    -2.33
     dilapidated
    -2.30
     contain
    -2.27
     desolate
    -2.22
    lgari
    -2.16
     sprawling
    -2.14
     tally
    -2.13
    ↵
    -2.13
     discontin
    -2.11
    POSITIVE LOGITS
    崀
    2.61
     selben
    2.38
    闿
    2.27
    Ꮠ
    2.17
    इटम
    2.17
    ться
    2.17
    鯪
    2.16
    2.16
     adoles
    2.06
     рад
    2.06
    Activations Density 0.003%

    No Known Activations