© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67729
    Prev
    Next
    INDEX
    Explanations

    official requests and documents

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

    The neuron fires on numeric values (digits and numbers, including those with decimal points).

    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
    ôtel
    -0.88
    playable
    -0.87
    atiana
    -0.87
     prototypes
    -0.86
    utella
    -0.83
     élect
    -0.81
    urka
    -0.81
     Drittel
    -0.80
    hates
    -0.80
    ergic
    -0.79
    POSITIVE LOGITS
     samtidigt
    0.93
     formal
    0.89
     ceremony
    0.87
     необхід
    0.85
     administrativa
    0.83
     certificates
    0.83
    jeti
    0.83
     registros
    0.83
     registra
    0.79
    ultimo
    0.79
    Activations Density 0.091%

    No Known Activations