© 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. 22-GEMMASCOPE-RES-131K
    4. 11149
    Prev
    Next
    INDEX
    Explanations

    tokens after specific words

    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_22/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
     by
    -1.05
     to
    -1.03
     dunklen
    -0.95
    に行きました
    -0.94
    keto
    -0.93
    стрее
    -0.90
     according
    -0.87
    に行ってきました
    -0.86
    обзор
    -0.85
     during
    -0.85
    POSITIVE LOGITS
     مباشرة
    1.12
    óculos
    0.98
    ℅
    0.91
    ଵ
    0.91
    чность
    0.91
    $__
    0.90
     høre
    0.86
     køb
    0.84
     choisi
    0.83
    nocześnie
    0.82
    Activations Density 0.050%

    No Known Activations