© 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. 22-GEMMASCOPE-RES-131K
    7. 54180
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

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

    The neuron flags standalone numeric literals (integer 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_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
    veux
    -0.93
     zj
    -0.92
    —-
    -0.92
    tierrez
    -0.88
     tiden
    -0.88
     与
    -0.87
    tul
    -0.85
    viseur
    -0.85
    kanak
    -0.85
     hidratante
    -0.84
    POSITIVE LOGITS
     ibland
    0.98
     möj
    0.98
     främ
    0.94
    了一些
    0.93
     därför
    0.92
     клини
    0.92
     föres
    0.91
    ghế
    0.91
    fjspx
    0.91
     Erster
    0.89
    Activations Density 0.027%

    No Known Activations