© 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. 31-GEMMASCOPE-2-RES-262K
    7. 54512
    Prev
    Next
    INDEX
    Explanations

    store stock

    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_31_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
     მხოლოდ
    0.52
    äre
    0.44
    üre
    0.43
     یہی
    0.42
     അതി
    0.41
     انٹر
    0.40
     variously
    0.39
     밀
    0.39
    والفقار
    0.39
     Без
    0.39
    POSITIVE LOGITS
    idc
    0.40
     чтобы
    0.38
    经常
    0.38
    /
    0.38
    頃
    0.38
     щоб
    0.38
    衰
    0.37
     TRPV
    0.37
     cambiamenti
    0.37
    宮
    0.37
    Activations Density 0.010%

    No Known Activations