© 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. 129649
    Prev
    Next
    INDEX
    Explanations

    area and place names

    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
     např
    -1.41
     alguém
    -1.27
    utica
    -1.24
     duele
    -1.23
    ripsi
    -1.23
    restling
    -1.21
    ربة
    -1.17
     consegui
    -1.16
     econó
    -1.16
     morrer
    -1.16
    POSITIVE LOGITS
     area
    1.52
     entire
    1.27
    𝒪
    1.19
     garaje
    1.16
     ――
    1.16
     incredi
    1.14
    ℉
    1.14
    מיד
    1.13
    unduh
    1.11
     dormitorio
    1.10
    Activations Density 0.035%

    No Known Activations