© 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. 34-GEMMASCOPE-RES-131K
    7. 89736
    Prev
    Next
    INDEX
    Explanations

    version beta

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

    The neuron activates on numeric tokens (i.e. standalone digits or multi‐digit number strings).

    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
    dialement
    -0.85
     overloading
    -0.82
    OfWeek
    -0.80
     Team
    -0.79
    老人
    -0.78
    Disclosure
    -0.76
    Ans
    -0.75
     competitively
    -0.75
    idjan
    -0.75
     tangible
    -0.75
    POSITIVE LOGITS
    BETA
    0.94
     BETA
    0.94
     beta
    0.93
    Neuer
    0.93
    beta
    0.93
     Möglich
    0.84
    version
    0.83
    Einzel
    0.82
     β
    0.82
     version
    0.82
    Activations Density 0.005%

    No Known Activations