© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31172
    Prev
    Next
    INDEX
    Explanations

    executable paths in /bin or /usr/bin

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron spotlights absolute filesystem paths (Unix-style paths starting with “/” and directory or binary names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     élabor
    -0.75
    Scoped
    -0.74
     wollte
    -0.73
     accelerometer
    -0.72
    営業
    -0.72
    multline
    -0.71
    coroutines
    -0.70
    tope
    -0.70
    bow
    -0.69
     explicó
    -0.69
    POSITIVE LOGITS
     executable
    2.59
    bin
    2.50
     execu
    2.41
     binaries
    2.30
     bin
    2.30
    executable
    2.27
    BIN
    2.17
     programs
    2.13
    Executable
    2.06
    Bin
    1.93
    Activations Density 0.213%

    No Known Activations