© 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. 11878
    Prev
    Next
    INDEX
    Explanations

    decay and increase over time

    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
     ſch
    -1.74
     maksi
    -1.59
    その時
    -1.54
    鹟
    -1.52
     fortun
    -1.50
    ſchen
    -1.48
    というわけで
    -1.48
    Добавлено
    -1.47
    brtc
    -1.47
     saada
    -1.46
    POSITIVE LOGITS
     is
    2.05
     of
    1.95
     I
    1.56
    ers
    1.38
     are
    1.36
     |
    1.35
     $
    1.30
     */
    1.29
     died
    1.28
    );
    1.24
    Activations Density 0.059%

    No Known Activations