© 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. 22-GEMMASCOPE-RES-131K
    7. 33781
    Prev
    Next
    INDEX
    Explanations

    Pontiac

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

    The neuron activates on numeric literal tokens (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     bilder
    -1.04
    簽
    -1.02
    While
    -0.99
     However
    -0.96
     komment
    -0.95
    printable
    -0.93
     vinci
    -0.91
     على
    -0.90
     jugend
    -0.90
    initializeApp
    -0.90
    POSITIVE LOGITS
     to
    1.27
     gebunden
    1.01
    いえば
    0.94
     for
    0.87
     léka
    0.86
     bekend
    0.86
    着一个
    0.82
     blight
    0.80
     отвечает
    0.80
     poden
    0.79
    Activations Density 0.001%

    No Known Activations