© 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. 34-GEMMASCOPE-RES-131K
    4. 103135
    Prev
    Next
    INDEX
    Explanations

    Moller Skycar

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

    The neuron strongly activates on numeric tokens (digit sequences), i.e. numbers.

    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
     ktor
    -0.91
     kolik
    -0.88
    Although
    -0.85
    Despite
    -0.84
    ета
    -0.83
    میزی
    -0.83
    よろしく
    -0.81
    jš
    -0.81
    غرب
    -0.81
    lastonbury
    -0.80
    POSITIVE LOGITS
    ↵
    0.95
     feat
    0.89
     consi
    0.84
    0.80
    delse
    0.80
    iap
    0.79
    Attn
    0.78
     neces
    0.78
     
    
    0.77
    μος
    0.77
    Activations Density 0.001%

    No Known Activations