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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 104265
    Prev
    Next
    INDEX
    Explanations

    running out of

    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
    ເຕ
    0.68
    冴
    0.64
     consente
    0.63
    듕
    0.61
    ৪০
    0.61
    လေး
    0.59
     radionu
    0.59
     Australie
    0.59
     testaceis
    0.58
     آهي
    0.57
    POSITIVE LOGITS
    an
    0.70
    s
    0.68
    ón
    0.63
    ar
    0.62
    ors
    0.60
    ัย
    0.60
    ime
    0.59
    z
    0.59
    et
    0.59
    ías
    0.57
    Activations Density 0.002%

    No Known Activations