© 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. 93237
    Prev
    Next
    INDEX
    Explanations

    resulting in conditions

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

    The neuron spikes on relatively long, domain-specific tokens (e.g. multi-syllable technical terms), i.e. words of substantial length typically found in scientific or medical 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
     læng
    -0.83
     vectores
    -0.81
     bütün
    -0.80
     nogle
    -0.79
     bất
    -0.79
     fehler
    -0.78
     fiecare
    -0.77
     Hohen
    -0.77
    cency
    -0.76
    magaz
    -0.76
    POSITIVE LOGITS
     resultant
    0.96
    ⸫
    0.92
     resulting
    0.89
     define
    0.85
    define
    0.85
    Consequently
    0.84
     Consequently
    0.82
     thereby
    0.80
     lateinit
    0.80
     upgrading
    0.78
    Activations Density 0.051%

    No Known Activations