© 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. 109588
    Prev
    Next
    INDEX
    Explanations

    copyright notices or "(C)"

    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
     [
    -0.81
     fifteen
    -0.80
     organizations
    -0.80
    }}(
    -0.79
     hopes
    -0.78
    ixeira
    -0.77
     וכו
    -0.77
    兼
    -0.76
    诸
    -0.75
    ↵↵↵↵↵↵↵↵
    -0.75
    POSITIVE LOGITS
    sic
    1.05
    中略
    0.89
    jeuner
    0.83
    disfraz
    0.82
     deviennent
    0.82
     donnés
    0.78
    の準備
    0.77
     cial
    0.77
    ίζει
    0.76
    Neces
    0.75
    Activations Density 0.113%

    No Known Activations