© 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. 32290
    Prev
    Next
    INDEX
    Explanations

    digital potentiometer

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

    The neuron activates on technical document headings and phrases describing in-circuit serial programming (ICSP) and high-voltage programming specifications for PIC microcontrollers.

    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
     Adjusted
    -0.94
     représentent
    -0.83
    ycznie
    -0.83
    私たちの
    -0.81
     Amended
    -0.81
    bukaan
    -0.81
    Например
    -0.79
     thereon
    -0.79
     Adapted
    -0.77
     — 
    -0.77
    POSITIVE LOGITS
     pous
    1.13
     internal
    1.12
     Januari
    1.07
    Lett
    1.02
    #)
    0.97
     internally
    0.96
    farms
    0.95
    unction
    0.94
     Intern
    0.92
     Februari
    0.91
    Activations Density 0.033%

    No Known Activations