© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131820
    Prev
    Next
    INDEX
    Explanations

    newness or recent events

    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_40_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
    tran
    0.39
    becomes
    0.39
    Become
    0.38
     завжди
    0.38
    PCR
    0.37
    ALWAYS
    0.37
    จน
    0.37
    㑨
    0.36
     ppl
    0.36
     بیت
    0.36
    POSITIVE LOGITS
     nouveau
    0.57
     新款
    0.53
    新技术
    0.51
     nueva
    0.49
     nouveaux
    0.49
    新鲜
    0.48
     නව
    0.46
    新
    0.46
     estética
    0.45
     الجديد
    0.45
    Activations Density 0.006%

    No Known Activations