© 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. 70114
    Prev
    Next
    INDEX
    Explanations

    python version numbers and code paths

    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
     for
    -2.14
     the
    -1.58
     an
    -1.43
     some
    -1.43
    надца
    -1.42
     stately
    -1.39
     سپس
    -1.37
     प्रयास
    -1.34
    ruhe
    -1.34
     zeigte
    -1.33
    POSITIVE LOGITS
     you
    1.58
    羮
    1.37
    IA
    1.30
    2
    1.30
     efectivamente
    1.30
     sprüche
    1.28
     likewise
    1.27
    crimination
    1.26
    I
    1.23
    または
    1.21
    Activations Density 0.068%

    No Known Activations