© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    right followed by another word

    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
    FOTOS
    -0.71
    련
    -0.71
    写真を
    -0.71
    Воз
    -0.71
     alın
    -0.70
     已
    -0.68
    lový
    -0.68
    doctype
    -0.68
    zeta
    -0.68
    オープン
    -0.67
    POSITIVE LOGITS
    sizing
    1.05
    ousness
    1.03
     Right
    0.97
    Right
    0.92
    ToLeft
    0.91
    teous
    0.90
     livelihood
    0.90
    డు
    0.88
    wing
    0.85
    cabulary
    0.85
    Activations Density 0.013%

    No Known Activations