© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38723
    Prev
    Next
    INDEX
    Explanations

    parts of compound words in code

    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
    ?”
    -3.30
    甞
    -3.03
    荦
    -2.92
    晅
    -2.83
    鑁
    -2.81
    🪬
    -2.53
    蓴
    -2.44
     natuurlijke
    -2.42
    鋌
    -2.41
    岽
    -2.39
    POSITIVE LOGITS
    It
    3.38
    9
    3.38
    If
    3.28
    They
    3.22
    You
    2.91
     رائع
    2.88
    These
    2.83
     为
    2.78
    t
    2.69
    ii
    2.58
    Activations Density 0.015%

    No Known Activations