© 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. 34-GEMMASCOPE-RES-131K
    7. 77352
    Prev
    Next
    INDEX
    Explanations

    shell commands and objects

    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
    zaken
    -0.76
     Pamp
    -0.75
     Pab
    -0.72
    CHAIN
    -0.69
    了我
    -0.69
    robes
    -0.69
     munch
    -0.69
    ربية
    -0.69
    пря
    -0.68
     Droit
    -0.68
    POSITIVE LOGITS
     Shell
    1.57
    Shell
    1.37
     shells
    1.11
     shell
    1.11
    殼
    1.03
     Shells
    1.02
    SHELL
    0.99
    shell
    0.97
     SHELL
    0.93
    壳
    0.84
    Activations Density 0.010%

    No Known Activations