© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59820
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Where you are"

    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
    และ
    -2.88
    葙
    -2.73
    U
    -2.25
    也会
    -1.96
    A
    -1.95
    莚
    -1.94
    }
    -1.93
     compagnon
    -1.92
     cementerio
    -1.88
    琑
    -1.88
    POSITIVE LOGITS
    </sup>
    2.69
     Who
    2.42
    ве
    2.36
    咐
    2.05
     они
    2.05
     Why
    2.03
     Where
    2.03
     Those
    1.98
    若是
    1.98
    nologia
    1.95
    Activations Density 0.012%

    No Known Activations