© 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. 22-GEMMASCOPE-RES-131K
    7. 33014
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

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

    The neuron never fires—it does not detect any token patterns (it remains inactive).

    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
    fæ
    -1.08
    ménage
    -1.05
    centerTitle
    -1.02
    rinho
    -0.99
    baomidou
    -0.98
    拴
    -0.97
     industrielle
    -0.96
    keyboardType
    -0.93
     visuelle
    -0.93
     ideen
    -0.93
    POSITIVE LOGITS
     gesamten
    0.90
     sämtliche
    0.83
    בס
    0.82
    いため
    0.82
    Clic
    0.81
    Forme
    0.81
     заканчи
    0.81
    Ered
    0.80
    าง
    0.79
     チェック
    0.78
    Activations Density 0.015%

    No Known Activations