© 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. 65785
    Prev
    Next
    INDEX
    Explanations

    manage applications, information, or resources

    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
     Unterschiede
    -2.34
     culminating
    -2.27
     erweiter
    -2.22
    媼
    -2.19
     Pesquisa
    -2.19
     verheir
    -2.16
     dostępne
    -2.13
    旆
    -2.11
    2
    -2.11
     Segurança
    -2.05
    POSITIVE LOGITS
    橚
    2.88
    曁
    2.80
    呖
    2.59
    鸯
    2.34
    さてさて
    2.34
     постоянно
    2.30
     thrilling
    2.25
     یک
    2.23
    蔔
    2.20
    ا
    2.19
    Activations Density 0.017%

    No Known Activations