© 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. 129504
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation!

    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
    '
    -1.45
     (
    -1.27
    -1.26
     canadien
    -1.18
    　　　　　
    -1.17
    ссор
    -1.17
    <sub>
    -1.14
                    
    -1.14
     chinois
    -1.14
     acides
    -1.13
    POSITIVE LOGITS
     Ausführungen
    1.35
    曁
    1.34
     berbagai
    1.33
     podría
    1.32
     alcune
    1.28
    allible
    1.27
     disposiciones
    1.27
     tornou
    1.26
     ワイン
    1.25
     mudou
    1.24
    Activations Density 0.016%

    No Known Activations