© 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. 82339
    Prev
    Next
    INDEX
    Explanations

    placement or moving aside

    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
     Sinclair
    -0.76
    Falta
    -0.74
     évé
    -0.73
    람
    -0.73
     gustó
    -0.73
    escolar
    -0.72
    Amar
    -0.72
    떻
    -0.71
     edile
    -0.71
    embley
    -0.71
    POSITIVE LOGITS
     aside
    6.78
    aside
    4.38
    Aside
    3.58
     Aside
    3.44
     apart
    2.78
     notwithstanding
    2.48
     aparte
    2.28
    apart
    2.08
     Apart
    1.88
    Apart
    1.86
    Activations Density 0.037%

    No Known Activations