© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236549
    Prev
    Next
    INDEX
    Explanations

    dupatta, help, flexibility, ship, disclosure, ticket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expressões
    0.52
    薜
    0.51
     expressão
    0.49
    ി
    0.49
     победи
    0.48
     potência
    0.48
     ligação
    0.47
    setCellValue
    0.46
    ель
    0.46
     мобиль
    0.46
    POSITIVE LOGITS
     Continuing
    0.53
    nin
    0.46
     outlining
    0.43
    ojs
    0.43
    ],
    0.43
    <eos>
    0.42
    Continuing
    0.42
     برقرار
    0.42
    length
    0.41
     continuing
    0.41
    Activations Density 0.000%

    No Known Activations