© 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. 22-GEMMASCOPE-RES-131K
    7. 13557
    Prev
    Next
    INDEX
    Explanations

    HttpClient code

    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_22/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
    .”
    -2.81
    hasMoreElements
    -2.28
     But
    -2.06
    依靠
    -1.97
     igenom
    -1.80
     definately
    -1.73
    袮
    -1.70
    疼痛
    -1.66
     разом
    -1.66
    h
    -1.66
    POSITIVE LOGITS
    {
    3.11
    ]
    2.25
     druga
    2.05
    <bos>
    1.98
    紧接着
    1.84
     diseñadores
    1.83
    𓁹
    1.79
    冧
    1.77
     faudrait
    1.76
    鋌
    1.76
    Activations Density 0.001%

    No Known Activations