© 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. 73028
    Prev
    Next
    INDEX
    Explanations

    start of phrases

    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
    }
    -1.16
    ющие
    -1.06
    никам
    -1.05
     лука
    -1.05
     дополнительных
    -1.03
    зде
    -1.02
     Verenig
    -1.02
    -};
    -1.01
    hemp
    -1.00
     
    -0.99
    POSITIVE LOGITS
    ஒ
    1.31
    excellents
    1.25
     Sortiment
    1.23
    當時
    1.22
    CurtirCurtir
    1.21
     мы
    1.20
    ḿ
    1.17
    מעות
    1.16
     niebla
    1.16
     geprü
    1.16
    Activations Density 0.000%

    No Known Activations