© 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. 131150
    Prev
    Next
    INDEX
    Explanations

    medical terms, types of music, food items, and scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    MacBook Pro, step by step

    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
    maları
    0.54
    ᱘
    0.54
     വരെ
    0.53
    戾
    0.53
    となる
    0.51
    ামুটি
    0.50
     панели
    0.50
    uć
    0.50
    を除く
    0.50
     масштаб
    0.50
    POSITIVE LOGITS
    </strong>
    0.52
     isn
    0.50
     will
    0.47
    zys
    0.46
    </td>
    0.45
     interp
    0.43
     --->
    0.43
     findAll
    0.43
     advantage
    0.43
     predic
    0.43
    Activations Density 0.001%

    No Known Activations