© 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. 82969
    Prev
    Next
    INDEX
    Explanations

    Estimated monthly

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

    The neuron strongly activates on numeric tokens (digits) and related numeric punctuation.

    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
    ']);
    -0.85
    centerX
    -0.84
    >−
    -0.82
    =
    -0.81
    CrossRef
    -0.80
     kita
    -0.80
    ∽
    -0.79
    kém
    -0.79
    HSSF
    -0.77
     island
    -0.77
    POSITIVE LOGITS
     Axios
    1.38
    Driving
    1.24
     Driving
    1.15
     driving
    1.09
    driving
    1.00
     why
    0.97
     axios
    0.92
     skyl
    0.91
    achery
    0.89
    Axios
    0.89
    Activations Density 0.009%

    No Known Activations