© 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. 83704
    Prev
    Next
    INDEX
    Explanations

    fortune smiles or fortunes

    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
    gebraucht
    -0.91
     deliciosos
    -0.90
    有哪些
    -0.86
    轡
    -0.85
    媼
    -0.83
     cucchia
    -0.83
    Приготовление
    -0.82
    定休日
    -0.82
    ının
    -0.82
    nika
    -0.80
    POSITIVE LOGITS
     fortune
    1.68
     teller
    1.59
     cookie
    1.36
    teller
    1.30
     Fortune
    1.24
    Fortune
    1.20
    fortune
    1.19
     fortunes
    1.16
    fav
    1.10
     Fortun
    1.10
    Activations Density 0.008%

    No Known Activations