© 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. 10-GEMMASCOPE-RES-131K
    7. 118834
    Prev
    Next
    INDEX
    Explanations

    human experiences and existence

    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
     such
    -1.59
    ⩴
    -1.44
    自己
    -1.40
     kedua
    -1.37
    هما
    -1.34
     itali
    -1.30
     analisis
    -1.29
    awatan
    -1.28
    rateful
    -1.27
     nuov
    -1.27
    POSITIVE LOGITS
    ࿚
    1.46
     who
    1.42
    古屋
    1.38
     kteří
    1.32
     divertidas
    1.30
     illustrious
    1.26
    最后由
    1.26
    ları
    1.26
     geniales
    1.25
     Ön
    1.24
    Activations Density 0.136%

    No Known Activations