© 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. 22-GEMMASCOPE-RES-131K
    4. 13363
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    ようだ
    -0.98
    Merkmale
    -0.96
     baik
    -0.94
     Staaten
    -0.93
     and
    -0.91
    ี่ยว
    -0.91
    펠
    -0.90
    šte
    -0.89
    when
    -0.89
    expect
    -0.88
    POSITIVE LOGITS
    で
    1.21
    が
    1.20
    は大
    1.20
    を
    1.17
    はその
    1.14
    は
    1.13
     защото
    1.13
     Kräuter
    1.12
    に
    1.10
     '/':
    1.09
    Activations Density 0.210%

    No Known Activations