© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59264
    Prev
    Next
    INDEX
    Explanations

    programming code structure

    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
     AGR
    -0.94
     最高
    -0.86
     både
    -0.84
    ѳ
    -0.82
     evidencia
    -0.81
     notwithstanding
    -0.81
    ンテージ
    -0.79
     únicamente
    -0.79
     chai
    -0.78
    🥭
    -0.78
    POSITIVE LOGITS
     Hock
    0.88
     Akte
    0.84
     But
    0.82
     влияет
    0.80
     oldValue
    0.80
    stderr
    0.79
    цкого
    0.79
     artificiales
    0.77
    ##
    0.77
    мі
    0.77
    Activations Density 0.027%

    No Known Activations