© 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. 34-GEMMASCOPE-RES-131K
    7. 35010
    Prev
    Next
    INDEX
    Explanations

    based onmake itversion is

    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_34/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
    𝙉
    -0.74
    ὰ
    -0.73
    Sr
    -0.71
    饕
    -0.71
    ('../
    -0.71
     Вели
    -0.71
     охо
    -0.69
     Derivation
    -0.69
    ละคร
    -0.68
    Initializer
    -0.68
    POSITIVE LOGITS
    
    0.97
     igjen
    0.84
    feof
    0.83
    ouch
    0.82
     untitled
    0.82
     малы
    0.82
    Exemples
    0.82
    ughter
    0.82
    заи
    0.81
    acts
    0.81
    Activations Density 0.004%

    No Known Activations