© 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. 70651
    Prev
    Next
    INDEX
    Explanations

    between two or more things

    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
    </b>
    -1.61
     髪型
    -1.49
    絰
    -1.44
     ſch
    -1.43
     accessoire
    -1.39
    ㈬
    -1.38
    壜
    -1.36
    水槽
    -1.34
     pharmacie
    -1.34
    直径
    -1.34
    POSITIVE LOGITS
     other
    1.95
    :
    1.71
     of
    1.60
    for
    1.57
    了过来
    1.55
     previous
    1.52
    A
    1.49
     respective
    1.48
     there
    1.38
     we
    1.37
    Activations Density 0.048%

    No Known Activations