© 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. 22128
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    쨩
    -2.27
    鼍
    -2.23
    鼱
    -2.22
    
    -2.17
    耵
    -2.09
    卝
    -2.06
    薆
    -1.95
     Wład
    -1.91
    ︲
    -1.89
    鱨
    -1.87
    POSITIVE LOGITS
    This
    2.17
    Also
    2.16
    For
    2.13
    There
    2.11
     with
    2.06
    Usually
    2.05
     Usually
    2.03
    It
    2.03
    These
    2.03
     and
    2.02
    Activations Density 0.255%

    No Known Activations