© 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. 45684
    Prev
    Next
    INDEX
    Explanations

    copy of license

    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
    Jürgen
    -0.91
    Sebagai
    -0.86
    Sekarang
    -0.81
    رمز
    -0.79
     helped
    -0.79
    ρίζ
    -0.78
    Sebelum
    -0.77
     any
    -0.77
    ΩΝ
    -0.77
    Berdasarkan
    -0.77
    POSITIVE LOGITS
     of
    1.48
     that
    1.17
    though
    0.92
    の一部
    0.86
    OfType
    0.84
    Xa
    0.82
     tinged
    0.82
     absurd
    0.81
    andu
    0.80
    这种
    0.80
    Activations Density 0.002%

    No Known Activations