© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    DisplayNameDisplayNameDisplayName

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

    The neuron activates on tokens containing numbers—i.e. numeric values or identifiers made up of digits.

    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
     Perhaps
    -1.20
     Surprisingly
    -1.20
     When
    -1.17
     Although
    -1.16
     During
    -1.16
     Since
    -1.12
     Unlike
    -1.12
     While
    -1.10
    Surprisingly
    -1.08
     for
    -1.06
    POSITIVE LOGITS
    eight
    1.05
     vatten
    1.04
     terminer
    1.01
     momente
    1.00
     dagar
    0.98
     ſt
    0.97
     Justiça
    0.97
     creativos
    0.97
     opdracht
    0.97
    }\
    0.96
    Activations Density 0.001%

    No Known Activations