© 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. 58150
    Prev
    Next
    INDEX
    Explanations

    the NFL

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

    The neuron primarily activates on numeric tokens (especially multi‐digit numbers such as years or competition statistics).

    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
    ࿚
    -1.16
    纰
    -1.01
     actitud
    -1.00
    子は
    -0.98
     Schub
    -0.97
     identifiable
    -0.96
     vznik
    -0.94
     canales
    -0.94
    귤
    -0.93
    lations
    -0.92
    POSITIVE LOGITS
     last
    1.38
     recent
    1.27
     recently
    1.09
     äußerst
    1.07
     latest
    1.05
     kürzlich
    1.03
     récemment
    0.97
     teuer
    0.97
     delayed
    0.96
     ২০১
    0.96
    Activations Density 0.122%

    No Known Activations