© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84592
    Prev
    Next
    INDEX
    Explanations

    RaspberryPI, MYSQL, MAC, HZ

    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
     we
    -1.78
     those
    -1.62
     consequently
    -1.35
     practically
    -1.34
     both
    -1.32
     substantially
    -1.31
    }}$
    -1.30
     być
    -1.28
     mostly
    -1.28
     possibly
    -1.24
    POSITIVE LOGITS
    为什么会
    1.65
    dateien
    1.45
     Verhält
    1.44
     Quien
    1.43
     تعت
    1.42
    ibrary
    1.41
    为什么
    1.40
    唿
    1.38
     Erfol
    1.38
     Todas
    1.38
    Activations Density 0.231%

    No Known Activations