© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83983
    Prev
    Next
    INDEX
    Explanations

    facebook api calls and errors

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

    The main thing this neuron does is detect numeric tokens (any standalone numbers or digit‐containing strings).

    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
    gemini
    -0.80
    igten
    -0.80
     tiến
    -0.79
     setUsername
    -0.73
     comerci
    -0.73
    Territory
    -0.73
    uangan
    -0.72
    ╗
    -0.72
    ισ
    -0.72
    Titan
    -0.71
    POSITIVE LOGITS
     FB
    1.45
     Facebook
    1.26
    Facebook
    1.25
     fb
    1.23
    FB
    1.21
    xfb
    1.16
     facebook
    1.15
     FACEBOOK
    1.13
     Fb
    0.95
    fbc
    0.92
    Activations Density 0.025%

    No Known Activations