© 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. 104804
    Prev
    Next
    INDEX
    Explanations

    awareness of surroundings

    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
    </i>
    -1.66
     meestal
    -1.48
     untuk
    -1.44
    нку
    -1.39
    וּ
    -1.33
    ри
    -1.30
     чтобы
    -1.21
     for
    -1.20
     поскольку
    -1.20
    "))
    -1.18
    POSITIVE LOGITS
     them
    1.59
    过来了
    1.45
     today
    1.38
     surrounding
    1.34
    引き続き
    1.34
     撮り
    1.33
    umbledore
    1.32
    gunaan
    1.29
     limpa
    1.29
    uterte
    1.27
    Activations Density 0.018%

    No Known Activations