© 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. 34-GEMMASCOPE-RES-131K
    7. 47540
    Prev
    Next
    INDEX
    Explanations

    plug housing

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

    The neuron is highly sensitive to numeric tokens (digits or multi‐digit numbers) in the text.

    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
     exempl
    -0.81
     electrocardio
    -0.79
     exemplaires
    -0.74
     exacer
    -0.74
    ◖
    -0.73
    lares
    -0.69
    婕
    -0.69
    +(\
    -0.68
    ushman
    -0.66
    購物
    -0.66
    POSITIVE LOGITS
    dagog
    0.79
    SYNC
    0.77
    companion
    0.77
     FAST
    0.77
     porta
    0.77
    Disposable
    0.74
     LV
    0.73
     METHOD
    0.73
     correspon
    0.73
     TIME
    0.72
    Activations Density 0.027%

    No Known Activations