© 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. 39363
    Prev
    Next
    INDEX
    Explanations

    .NET code components

    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
     they
    -2.27
     mereka
    -1.83
     их
    -1.70
     their
    -1.64
    Their
    -1.63
     Their
    -1.53
     jejich
    -1.52
     они
    -1.42
     їх
    -1.42
    期刊论文
    -1.38
    POSITIVE LOGITS
     our
    1.47
    </table>
    1.45
    *}[
    1.35
    我會
    1.34
     to
    1.34
    在你
    1.32
    ds
    1.31
    }}>
    1.30
    エール
    1.29
     nasze
    1.28
    Activations Density 0.003%

    No Known Activations