© 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. 34-GEMMASCOPE-RES-131K
    7. 91490
    Prev
    Next
    INDEX
    Explanations

    struggling or lost

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

    This neuron responds to clause‐separating punctuation (especially commas and other phrase breaks).

    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
     limón
    -1.05
     się
    -1.04
     disparu
    -1.02
     jednak
    -1.02
     פֿ
    -1.00
     assurent
    -0.98
    噘
    -0.98
    ticular
    -0.97
    そちら
    -0.96
     проживания
    -0.96
    POSITIVE LOGITS
     unable
    2.98
    unable
    2.03
    Unable
    1.94
     surrounded
    1.94
     facing
    1.87
     incapable
    1.68
     with
    1.66
     Unable
    1.59
     without
    1.57
     stuck
    1.53
    Activations Density 0.087%

    No Known Activations