© 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. 48333
    Prev
    Next
    INDEX
    Explanations

    Japanese city names and Indian city names

    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
     –
    -3.84
    <
    -2.81
    1
    -2.70
    ’
    -2.66
    2
    -2.63
            
    -2.50
     {
    -2.47
     t
    -2.42
    </h1>
    -2.42
    }=
    -2.36
    POSITIVE LOGITS
     It
    3.03
    鸝
    2.77
    They
    2.38
    ſures
    2.36
    ྵ
    2.25
    大体
    2.25
     impone
    2.22
    钹
    2.22
    夘
    2.20
    </em>
    2.19
    Activations Density 0.000%

    No Known Activations