© 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. 40360
    Prev
    Next
    INDEX
    Explanations

    list of contributors

    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
    wendig
    -1.59
     dando
    -1.32
     bibliothèque
    -1.29
     leur
    -1.25
    脚注
    -1.24
    際に
    -1.24
    ofern
    -1.23
     pertence
    -1.23
     faisant
    -1.23
     「
    -1.23
    POSITIVE LOGITS
     this
    2.08
     your
    1.93
     and
    1.87
     how
    1.62
     our
    1.45
     which
    1.41
     about
    1.38
     these
    1.28
    ]$,
    1.26
     also
    1.24
    Activations Density 0.105%

    No Known Activations