© 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. 59202
    Prev
    Next
    INDEX
    Explanations

    Southern Europe Mediterranean

    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
     burbujas
    -1.18
    atiques
    -1.15
    或者
    -1.14
     animés
    -1.14
    ↵↵↵↵
    -1.14
    ｙ
    -1.13
    褔
    -1.13
    Hugs
    -1.13
    ；
    -1.13
     otras
    -1.13
    POSITIVE LOGITS
     cro
    1.27
     Алек
    1.23
    足以
    1.11
     prepare
    1.10
     predict
    1.09
    te
    1.08
    掷
    1.08
     quintessential
    1.05
     cinq
    1.04
    ecan
    1.04
    Activations Density 0.045%

    No Known Activations