© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76135
    Prev
    Next
    INDEX
    Explanations

    silence and quiet

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

    The neuron fires on past‐perfect verb constructions (i.e. “had” followed by a past participle).

    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
     fibroblasts
    -0.78
    솟
    -0.76
    raszam
    -0.76
    sunny
    -0.74
    ەر
    -0.72
    binaan
    -0.71
    igi
    -0.71
    ガネ
    -0.71
    lightly
    -0.70
    鰐
    -0.70
    POSITIVE LOGITS
     silence
    6.16
    Silence
    4.75
     Silence
    4.69
    silence
    4.41
     silent
    4.34
     silencio
    3.69
     quiet
    3.53
    silent
    3.38
     silenzio
    3.22
     Silent
    3.09
    Activations Density 0.043%

    No Known Activations