© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13239
    Prev
    Next
    INDEX
    Explanations

    legal citations and statutes

    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
     grigio
    -1.30
    ૉ
    -1.29
     ۱۶
    -1.27
     ۱۴
    -1.24
     dégust
    -1.23
     минера
    -1.21
     '.';
    -1.20
     τὸν
    -1.19
    ἵ
    -1.18
     ܐ
    -1.12
    POSITIVE LOGITS
    ̳
    1.25
    anglicky
    1.23
    余额
    1.23
     after
    1.20
     spodnie
    1.20
     requirements
    1.16
    nagyobb
    1.16
     před
    1.14
     procesador
    1.14
     metav
    1.13
    Activations Density 0.036%

    No Known Activations