© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109789
    Prev
    Next
    INDEX
    Explanations

    lying down or resting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    bustible
    -0.77
     Bioinformatics
    -0.77
     .=
    -0.74
    加油
    -0.74
     пун
    -0.72
     Standort
    -0.72
     disponible
    -0.71
     შ
    -0.70
    akad
    -0.69
    ="{{
    -0.69
    POSITIVE LOGITS
     lying
    5.53
     lie
    4.38
     Lying
    4.09
    Lying
    4.03
     lies
    3.91
     lay
    3.84
    lying
    3.59
     laying
    3.56
     лежа
    3.39
    Lie
    3.23
    Activations Density 0.059%

    No Known Activations