© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88534
    Prev
    Next
    INDEX
    Explanations

    knowledge base articles

    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
     tries
    0.64
     recettes
    0.63
     новым
    0.61
     нов
    0.58
    ベント
    0.57
     учета
    0.57
    ábado
    0.57
    ه
    0.56
    ising
    0.56
    ١
    0.55
    POSITIVE LOGITS
    um
    0.73
    ur
    0.63
    ara
    0.60
    umy
    0.58
     substation
    0.57
    ad
    0.55
    imizi
    0.54
    ay
    0.53
     immun
    0.53
     Election
    0.52
    Activations Density 0.004%

    No Known Activations