© 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. 10-GEMMASCOPE-RES-131K
    7. 47489
    Prev
    Next
    INDEX
    Explanations

    imperfections, imperfect, impermeable

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

    The neuron activates on the character sequence “imper” (most prominently in the word “imperfections”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     technisch
    -2.97
     verbre
    -2.92
     gefe
    -2.80
    湏
    -2.58
     blau
    -2.58
     respective
    -2.56
     messen
    -2.55
    ༵
    -2.55
    𞤤
    -2.53
     nimmer
    -2.52
    POSITIVE LOGITS
    ↵
    3.61
    d
    3.05
    7
    3.02
    .
    2.83
    6
    2.77
    5
    2.67
    what
    2.59
    4
    2.56
    8
    2.55
    You
    2.53
    Activations Density 0.003%

    No Known Activations