© 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. 34-GEMMASCOPE-RES-131K
    7. 102737
    Prev
    Next
    INDEX
    Explanations

    make command and makefiles

    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_34/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
    Ừ
    -0.78
     quente
    -0.77
     bourgeoisie
    -0.72
     cypress
    -0.71
     facades
    -0.70
     bourgeois
    -0.70
     gallows
    -0.69
    ARK
    -0.69
    pentru
    -0.69
    anız
    -0.68
    POSITIVE LOGITS
     make
    2.00
    make
    1.72
     Make
    1.69
    Make
    1.46
     MAKE
    1.45
    Makefile
    1.20
    MAKE
    1.17
     Makefile
    1.13
     clean
    1.09
     makes
    1.05
    Activations Density 0.070%

    No Known Activations