© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111668
    Prev
    Next
    INDEX
    Explanations

    mathematical notation symbols

    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
    There
    -3.39
    This
    -3.19
    It
    -3.06
    When
    -3.02
    They
    -3.00
    While
    -2.89
     Luckily
    -2.69
    Unfortunately
    -2.66
    These
    -2.58
     Interestingly
    -2.58
    POSITIVE LOGITS
    瓛
    2.66
    {
    2.33
    \
    2.28
    籥
    2.16
    },
    2.09
    ſche
    2.08
     {
    2.03
     &
    2.00
    箧
    1.99
    ꜄
    1.99
    Activations Density 0.150%

    No Known Activations