© 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. 22-GEMMASCOPE-RES-131K
    7. 15066
    Prev
    Next
    INDEX
    Explanations

    past participles followed by context

    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_22/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
     Geografía
    -1.00
    สิ่ง
    -0.98
    虽然
    -0.96
    使用
    -0.96
    が
    -0.95
    内容
    -0.93
    に対して
    -0.91
    梳
    -0.88
     extérieurs
    -0.88
    свя
    -0.88
    POSITIVE LOGITS
     by
    1.73
     in
    1.60
     any
    1.29
     on
    1.27
     their
    1.23
     there
    1.18
     across
    1.12
     needed
    1.12
     required
    1.06
     occurring
    1.03
    Activations Density 0.085%

    No Known Activations