© 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. 39590
    Prev
    Next
    INDEX
    Explanations

    idiom, idiomatic, idiopathic

    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
     were
    -3.13
     "
    -2.83
    ਞ
    -2.72
     vorigen
    -2.64
    >
    -2.50
     whom
    -2.45
    谖
    -2.39
    es
    -2.27
    很好的
    -2.20
    口中
    -2.14
    POSITIVE LOGITS
    翾
    2.39
    ๐
    2.22
    Cinta
    2.20
    龚
    2.13
    责编
    2.13
    鹟
    2.13
    锷
    2.09
    Tapi
    2.08
    也會
    2.05
    쩡
    2.02
    Activations Density 0.006%

    No Known Activations