© 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. 77692
    Prev
    Next
    INDEX
    Explanations

    position, POSIX, Postel

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

    The neuron fires on position metadata in code or JSON—specifically tokens like “pos” and the numeric values that follow.

    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
     Frem
    -0.89
    ある
    -0.86
    had
    -0.85
     notorious
    -0.77
     hinted
    -0.77
     now
    -0.77
    写作
    -0.76
     missing
    -0.75
    Made
    -0.75
     also
    -0.74
    POSITIVE LOGITS
     pos
    1.42
     Pos
    1.38
    posits
    1.23
    getPos
    1.22
    sibilities
    1.15
    tition
    1.14
     strpos
    1.08
     Position
    1.06
    Pos
    1.02
    bori
    1.01
    Activations Density 0.007%

    No Known Activations