© 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. 105132
    Prev
    Next
    INDEX
    Explanations

    either of

    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
    Usually
    -1.91
    Surprisingly
    -1.87
    Sometimes
    -1.75
    Probably
    -1.74
    Quite
    -1.73
    Several
    -1.72
    tó
    -1.72
    Honestly
    -1.70
    Perhaps
    -1.69
    Very
    -1.68
    POSITIVE LOGITS
     hizo
    1.65
    _
    1.59
     I
    1.59
    就可以
    1.52
    либо
    1.50
     tampoco
    1.46
     than
    1.42
     deter
    1.38
    是用
    1.31
    ее
    1.30
    Activations Density 0.023%

    No Known Activations