© 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. 74549
    Prev
    Next
    INDEX
    Explanations

    links and citations

    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
    It
    -3.16
    ;
    -3.09
    ve
    -3.05
     After
    -2.92
    The
    -2.92
    ’
    -2.86
    They
    -2.86
    After
    -2.84
    m
    -2.80
    When
    -2.78
    POSITIVE LOGITS
    饪
    3.64
    樒
    3.61
    鑁
    3.61
    筇
    3.38
    籀
    3.22
    縢
    3.03
     говорил
    3.03
    鱚
    3.02
     использовании
    2.94
    甞
    2.92
    Activations Density 0.100%

    No Known Activations