© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95613
    Prev
    Next
    INDEX
    Explanations

    sector

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

    The neuron chiefly responds to standalone numeric tokens (e.g. reference numbers or 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_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
    っております
    -1.15
    ennung
    -1.11
    ctivo
    -1.07
     понадоби
    -1.05
     urb
    -1.05
     Oppo
    -1.05
    otho
    -1.02
    ⚛
    -1.02
    ieme
    -1.01
     Majesté
    -0.99
    POSITIVE LOGITS
     another
    1.25
     again
    1.22
    <h3>
    1.20
     lastly
    1.16
     Table
    1.13
     Another
    1.11
    .
    1.10
     some
    1.09
     continue
    1.07
    \
    1.07
    Activations Density 0.001%

    No Known Activations