© 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. 22-GEMMASCOPE-RES-131K
    7. 84140
    Prev
    Next
    INDEX
    Explanations

    questions and numerical data

    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
    がありますが
    -1.30
    Komentar
    -1.29
    archical
    -1.23
    🐛
    -1.21
    時間は
    -1.20
    Teknik
    -1.17
    牴
    -1.17
    Lịch
    -1.17
    Zubereitung
    -1.16
    cestor
    -1.15
    POSITIVE LOGITS
    J
    1.23
    G
    1.16
    に変更
    1.13
    C
    1.09
    為に
    1.06
    t
    1.05
    R
    1.03
    T
    1.03
    F
    1.03
    el
    1.02
    Activations Density 0.005%

    No Known Activations