© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14808
    Prev
    Next
    INDEX
    Explanations

    mixed language context

    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
     względem
    -1.68
     pirm
    -1.59
    ствии
    -1.48
     igjen
    -1.45
     ettei
    -1.44
     сиро
    -1.42
     THE
    -1.41
     they
    -1.41
     bodem
    -1.40
    eryllium
    -1.39
    POSITIVE LOGITS
    WRENCE
    1.84
    //#
    1.63
     egenskaper
    1.62
     atentos
    1.55
     malen
    1.52
     ampliar
    1.50
    `;
    1.49
     还
    1.48
     recompensa
    1.45
    </sup>
    1.44
    Activations Density 0.020%

    No Known Activations