© 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. 10-GEMMASCOPE-RES-131K
    4. 105451
    Prev
    Next
    INDEX
    Explanations

    disposed with location prepositions

    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_10/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
    Also
    -2.17
    Could
    -1.95
    All
    -1.91
    }
    -1.88
    he
    -1.88
    Does
    -1.83
    Would
    -1.83
    Their
    -1.81
    During
    -1.75
    At
    -1.73
    POSITIVE LOGITS
    “
    1.65
     zahlreiche
    1.61
    trooper
    1.60
     中式
    1.60
     was
    1.57
    <bos>
    1.57
    鱚
    1.55
    hahahaha
    1.51
    ارتمان
    1.51
    羕
    1.50
    Activations Density 0.002%

    No Known Activations