© 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. 22-GEMMASCOPE-RES-131K
    7. 38262
    Prev
    Next
    INDEX
    Explanations

    mathematical operations like multiply, subtract, average, raise

    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_22/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
    m
    -1.29
    Q
    -1.23
    This
    -1.21
    At
    -1.20
    ほとんど
    -1.20
    en
    -1.17
    l
    -1.16
    =
    -1.14
     это
    -1.13
    的他
    -1.13
    POSITIVE LOGITS
     the
    2.89
     navigu
    1.27
    vriende
    1.24
    馘
    1.23
    狴
    1.23
    ܆
    1.23
    𓆏
    1.23
     ſol
    1.23
     estadounid
    1.21
     pérd
    1.21
    Activations Density 0.033%

    No Known Activations