© 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. 66730
    Prev
    Next
    INDEX
    Explanations

    web address

    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
    Currently
    -2.44
    Also
    -2.30
    You
    -2.28
    觧
    -2.27
    他の
    -2.25
    _
    -2.14
    ,’’
    -2.13
    蛧
    -2.11
    Here
    -2.08
    ﾈ
    -2.08
    POSITIVE LOGITS
    as
    3.13
     '
    2.73
    a
    2.67
    鲼
    2.61
    遢
    2.61
    硨
    2.39
    ى
    2.39
    /'
    2.34
    饧
    2.27
    к
    2.22
    Activations Density 0.003%

    No Known Activations