© 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. 222900
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ed', 'ing', or 'izes'

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

    younger generations

    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
    らは
    0.47
    𝐘
    0.47
    ContactBundle
    0.46
    𝙔
    0.46
    㐌
    0.45
    担
    0.45
     사건
    0.44
    ꫝ
    0.44
    ಿಕೊಂಡ
    0.42
    следование
    0.42
    POSITIVE LOGITS
     dominante
    0.52
    id
    0.49
     generalmente
    0.49
     benefici
    0.47
    ဟုတ်
    0.47
     semen
    0.46
     ((
    0.45
     (((
    0.45
     geralmente
    0.45
    ثمان
    0.44
    Activations Density 0.001%

    No Known Activations