© 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. 65236
    Prev
    Next
    INDEX
    Explanations

    android, google, and related software

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

    This neuron detects software‐and‐SDK identifiers and version tokens—especially Android/Google tool names and their version numbers.

    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
    Keynote
    -0.77
     Sedgwick
    -0.75
    gaver
    -0.73
    Inhoud
    -0.73
    FOTOS
    -0.71
    PRIME
    -0.70
     Yos
    -0.69
     Lettres
    -0.69
    بیر
    -0.69
    Portug
    -0.69
    POSITIVE LOGITS
     Pixel
    1.26
     Pie
    1.11
    Pixel
    0.96
    Pie
    0.87
     androidx
    0.86
    udio
    0.81
     pie
    0.79
     Oreo
    0.79
    corsi
    0.77
     chatbot
    0.76
    Activations Density 0.057%

    No Known Activations