© 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. 34-GEMMASCOPE-RES-131K
    7. 47948
    Prev
    Next
    INDEX
    Explanations

    French, Spanish, Italian, German, Turkish

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

    The neuron fires strongly on short two-letter prepositions meaning “in” (e.g. “in,” “en,” “em”) across different languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Effect
    -1.04
     effects
    -1.03
     Effects
    -1.02
     effect
    -1.02
     efecto
    -1.00
    effects
    -0.87
     EFFECTS
    -0.85
     effet
    -0.82
    effect
    -0.80
    Effects
    -0.79
    POSITIVE LOGITS
     depth
    0.91
    webp
    0.85
     trompe
    0.78
     lyre
    0.78
     stork
    0.77
    娇
    0.76
    ところは
    0.75
     fune
    0.75
     anom
    0.74
    Depth
    0.73
    Activations Density 0.040%

    No Known Activations