© 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. 64876
    Prev
    Next
    INDEX
    Explanations

    later, next, subsequent

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

    The neuron activates on numeric tokens (integers or decimals).

    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
     nawet
    -0.92
    cticide
    -0.84
    境的
    -0.84
     osal
    -0.83
    koff
    -0.82
    (©
    -0.81
     lait
    -0.79
     ју
    -0.78
    bebasan
    -0.78
     Lenny
    -0.77
    POSITIVE LOGITS
     another
    1.34
     later
    1.19
     counterpart
    1.09
     next
    1.06
    อีก
    1.05
     same
    1.04
     second
    0.98
     successivo
    0.98
     different
    0.91
     subsequent
    0.90
    Activations Density 0.169%

    No Known Activations