© 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. 22-GEMMASCOPE-RES-131K
    7. 27799
    Prev
    Next
    INDEX
    Explanations

    disable eslint

    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
     others
    -1.32
     tačiau
    -1.11
    ふと
    -1.09
     
    -1.07
    除此
    -1.06
     anderen
    -1.05
    s
    -1.03
    ファミ
    -1.02
    ご馳走
    -1.00
     his
    -0.99
    POSITIVE LOGITS
     sociaux
    1.30
    ولايات
    1.27
    НЫЙ
    1.21
     traditionnels
    1.20
     roligt
    1.19
    顧客
    1.19
     romana
    1.19
     odkazy
    1.17
     now
    1.16
     populaires
    1.16
    Activations Density 0.002%

    No Known Activations