© 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. 47802
    Prev
    Next
    INDEX
    Explanations

    following millennia

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

    The neuron strongly activates on multi‐digit numeric strings (i.e. sequences of digits such as dates, codes, references, or other numbers).

    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
     still
    -1.22
     other
    -1.20
     like
    -1.19
     but
    -1.16
     so
    -1.09
     now
    -1.04
     able
    -1.02
     designated
    -0.97
     did
    -0.96
     most
    -0.93
    POSITIVE LOGITS
    Hunting
    0.98
    ologique
    0.97
    brake
    0.94
    áticas
    0.94
    conducted
    0.91
     auta
    0.90
    atoes
    0.89
     lle
    0.88
    Voltaje
    0.87
    verlust
    0.85
    Activations Density 0.000%

    No Known Activations