© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52058
    Prev
    Next
    INDEX
    Explanations

    implies existence of patterns

    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
    ።
    0.59
     mejoras
    0.46
    мян
    0.46
    ጻ
    0.44
     처음
    0.44
     সর্বপ্রথম
    0.43
     своя
    0.43
    사용
    0.42
    Читать
    0.42
     короля
    0.42
    POSITIVE LOGITS
    อยู่ใน
    0.54
     în
    0.46
     routinely
    0.45
    ຢູ່ໃນ
    0.44
     moons
    0.43
     dalam
    0.43
     everywhere
    0.43
     verteilt
    0.43
     perpetually
    0.42
     ở
    0.41
    Activations Density 0.014%

    No Known Activations