© 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. 99509
    Prev
    Next
    INDEX
    Explanations

    ahead 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
     constantly
    -2.05
     termed
    -1.94
     p
    -1.91
     now
    -1.90
     occasionally
    -1.90
    “
    -1.88
     chiefly
    -1.83
     extraordinarily
    -1.82
     moderately
    -1.82
     unwavering
    -1.81
    POSITIVE LOGITS
     inoxydable
    2.34
     frança
    2.30
     anunció
    2.27
    蚨
    2.27
     aussit
    2.19
     anún
    2.14
    噲
    2.14
     estadounid
    2.13
    ientras
    2.09
    龅
    2.06
    Activations Density 0.003%

    No Known Activations