© 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. 11912
    Prev
    Next
    INDEX
    Explanations

    listing options or types

    np_acts-logits-general · gemini-2.5-flash-lite

    apostrophes in English contractions and possessives, especially within conversational or list-structured text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     diffeomorphism
    0.43
     தொடர்ந்து
    0.40
     pathologies
    0.40
     നടത്തിയ
    0.39
    roffenen
    0.39
    罹
    0.39
     conformational
    0.39
     metamorphosis
    0.38
     viciss
    0.38
    unoscut
    0.38
    POSITIVE LOGITS
    大小
    0.38
     trắng
    0.38
     종류
    0.36
    選び
    0.36
     either
    0.35
     или
    0.35
    或
    0.35
    <unused2125>
    0.34
    iranja
    0.34
     سواء
    0.34
    Activations Density 0.303%

    No Known Activations