© 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. 70812
    Prev
    Next
    INDEX
    Explanations

    package 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_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
    と思い
    -1.56
    k
    -1.38
     錠
    -1.31
    って思
    -1.30
    ”
    -1.29
     mehrere
    -1.25
     ältere
    -1.24
    纽
    -1.23
     TAMBÉM
    -1.23
     }
    -1.22
    POSITIVE LOGITS
     of
    2.13
    ᐕ
    1.73
     gmina
    1.45
     był
    1.43
    rachel
    1.43
     ulica
    1.39
     海岸
    1.38
     Они
    1.34
     escritores
    1.34
     Mère
    1.33
    Activations Density 0.002%

    No Known Activations