© 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. 33865
    Prev
    Next
    INDEX
    Explanations

    brand names

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

    The neuron strongly responds to standalone numeric tokens—like list or step numbers, version numbers, and model numbers—where digits appear as their own tokens.

    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
     when
    -1.37
    лтемелер
    -1.29
     their
    -1.15
     if
    -1.15
     musí
    -1.13
     Wirksamkeit
    -1.13
     саны
    -1.13
     Profitez
    -1.12
     Bewußt
    -1.08
     Erfüllung
    -1.08
    POSITIVE LOGITS
     erin
    1.12
    癱
    1.08
     qtd
    1.06
     💕
    1.06
     felipe
    1.05
     =$
    1.05
     juf
    1.05
     Hift
    1.04
     james
    1.03
    😫
    1.03
    Activations Density 0.091%

    No Known Activations