© 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. 27520
    Prev
    Next
    INDEX
    Explanations

    also, également, también

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

    This neuron fires on programming‐style punctuation tokens (especially underscores, braces, quotes, and operators) rather than ordinary words.

    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
     خواهد
    -1.05
     verificar
    -0.91
    šenie
    -0.90
     whoſe
    -0.88
     satisfies
    -0.86
    文句
    -0.86
     bruge
    -0.85
    orexia
    -0.85
     Schmerzen
    -0.85
    Mango
    -0.84
    POSITIVE LOGITS
     également
    1.22
     also
    1.07
     هناك
    1.05
     também
    1.04
    Also
    1.03
     otras
    1.02
     también
    1.00
     algunos
    1.00
    ContentLoaded
    0.98
    izacja
    0.96
    Activations Density 0.006%

    No Known Activations