© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14616
    Prev
    Next
    INDEX
    Explanations

    stays and travel dates

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

    The neuron is primarily triggered by numeric tokens (and related punctuation sequences like ellipses or standalone 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_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
     from
    -1.03
     hotell
    -0.99
     intemper
    -0.99
    empio
    -0.96
    ėk
    -0.96
     Making
    -0.95
    Q
    -0.94
    Hz
    -0.93
     Before
    -0.93
     jaja
    -0.93
    POSITIVE LOGITS
    couldn
    1.16
    €”
    1.13
    hort
    1.11
    ⛦
    1.08
    coherent
    1.08
     atletas
    1.05
    recently
    1.04
    вшись
    1.04
     THOUGHT
    1.04
     atún
    1.03
    Activations Density 0.001%

    No Known Activations