© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49544
    Prev
    Next
    INDEX
    Explanations

    conjunctions and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    en
    0.61
    ar
    0.54
     hearth
    0.46
    偕
    0.45
    pool
    0.45
    ensure
    0.44
    quele
    0.44
    tiempo
    0.42
    PATH
    0.42
    et
    0.42
    POSITIVE LOGITS
     χρήση
    0.57
     använda
    0.53
     যাত্রী
    0.52
     Анд
    0.52
     ඉතා
    0.52
     विजे
    0.51
     nových
    0.50
    Ǻ
    0.49
     будів
    0.48
     jus
    0.48
    Activations Density 0.000%

    No Known Activations