© 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. 130659
    Prev
    Next
    INDEX
    Explanations

    Internet of Things

    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
     这个
    -2.41
     While
    -2.34
    If
    -2.27
    minha
    -2.25
     這
    -2.25
    ㌔
    -2.20
     Bedürfn
    -2.17
    楽しみにして
    -2.16
     disesuaikan
    -2.14
    However
    -2.13
    POSITIVE LOGITS
    {
    3.75
    ]
    3.52
    le
    2.30
    }
    2.11
    ふれ
    2.08
    AS
    2.08
    튿
    2.03
    </strong>
    2.02
    ю
    2.00
    ↵↵
    1.99
    Activations Density 0.018%

    No Known Activations