© 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. 10-GEMMASCOPE-RES-131K
    4. 75664
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
    </sup>
    -1.83
     of
    -1.61
     kveld
    -1.56
    not
    -1.41
    ne
    -1.40
    which
    -1.39
    le
    -1.30
    la
    -1.29
    de
    -1.27
     also
    -1.26
    POSITIVE LOGITS
    を選ぶ
    1.39
     utilisés
    1.34
    因為
    1.27
    ANZA
    1.25
    繼續
    1.23
     Porque
    1.21
    といった
    1.20
    automotive
    1.19
    經常
    1.19
    gelang
    1.18
    Activations Density 0.033%

    No Known Activations