© 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. 47560
    Prev
    Next
    INDEX
    Explanations

    here as a reference

    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
     DOES
    -1.38
    }
    -1.37
    ’
    -1.36
     ungefär
    -1.34
    "]));
    -1.27
    "])
    -1.25
     примеру
    -1.21
    わ
    -1.18
     է
    -1.17
    recall
    -1.17
    POSITIVE LOGITS
     conduit
    1.49
    Заключение
    1.47
    联网
    1.47
    線が
    1.41
    っている
    1.40
     strongest
    1.33
     fashioned
    1.31
    andı
    1.30
     AGUA
    1.30
     would
    1.29
    Activations Density 0.006%

    No Known Activations