© 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. 65884
    Prev
    Next
    INDEX
    Explanations

    messaging, communication, and identifiers

    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
     because
    -1.50
     that
    -1.46
     a
    -1.23
    We
    -1.20
    YNAMICS
    -1.19
     AGAIN
    -1.19
     Remember
    -1.16
    k
    -1.15
     Still
    -1.14
     licht
    -1.14
    POSITIVE LOGITS
    ⡉
    1.37
    ерез
    1.36
     slams
    1.34
    anzug
    1.30
     邸
    1.30
    Studi
    1.28
    撂
    1.23
    credited
    1.23
    endola
    1.23
    惴
    1.22
    Activations Density 0.040%

    No Known Activations