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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71102
    Prev
    Next
    INDEX
    Explanations

    prepositions and relation 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
     godk
    -0.90
     thugs
    -0.89
     sonunda
    -0.89
     entsprechen
    -0.85
     outcomes
    -0.85
     eventually
    -0.82
    ▇
    -0.81
     samtidigt
    -0.80
    一座
    -0.79
     liksom
    -0.79
    POSITIVE LOGITS
     chính
    1.06
     próprio
    0.95
    ými
    0.93
     ourselves
    0.92
     propia
    0.92
    sprzed
    0.91
     造型
    0.91
    ண்டும்
    0.89
     from
    0.88
     OUR
    0.88
    Activations Density 0.075%

    No Known Activations