© 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. 10-GEMMASCOPE-RES-131K
    7. 21907
    Prev
    Next
    INDEX
    Explanations

    signs and comments

    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_10/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
    各種
    -1.49
    媜
    -1.47
    Harga
    -1.41
    7
    -1.40
    Tentang
    -1.40
    Achter
    -1.39
    5
    -1.38
    ментом
    -1.37
     zrobić
    -1.36
    要求
    -1.35
    POSITIVE LOGITS
    in
    1.48
    are
    1.38
    im
    1.36
     each
    1.33
    will
    1.32
     bilhões
    1.28
    齤
    1.27
    ского
    1.26
    枚目
    1.26
     Stoffe
    1.24
    Activations Density 0.048%

    No Known Activations