© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34640
    Prev
    Next
    INDEX
    Explanations

    black fruits, flowers, large, stone

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

    The neuron is highly responsive to numerical values (digits) in the text, such as measurements or counts.

    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
    responseType
    -1.30
    rebbe
    -1.30
    addHeader
    -1.29
     satılık
    -1.27
    PathVariable
    -1.27
     sadar
    -1.23
     konsult
    -1.22
    writeHead
    -1.22
     maail
    -1.19
     opsi
    -1.18
    POSITIVE LOGITS
     with
    1.46
    エリー
    1.06
    两位
    1.06
     största
    1.05
     there
    0.99
     碗
    0.99
     mesmas
    0.98
    :)
    0.96
    ～。
    0.95
    𝟑
    0.94
    Activations Density 0.004%

    No Known Activations