© 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. 13238
    Prev
    Next
    INDEX
    Explanations

    program requirement

    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
    蕺
    -1.95
    他们在
    -1.94
    Ꮏ
    -1.88
    ですが
    -1.80
    亟
    -1.63
     mereka
    -1.63
    鹚
    -1.63
     ellos
    -1.61
    ——”
    -1.57
    ！"
    -1.56
    POSITIVE LOGITS
    \
    1.80
    ).
    1.66
    as
    1.63
     lekko
    1.59
     arbeitete
    1.58
     женская
    1.57
     جایی
    1.57
     erlä
    1.53
     He
    1.48
     dług
    1.48
    Activations Density 0.000%

    No Known Activations