© 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-16K
    7. 10961
    Prev
    Next
    INDEX
    Explanations

    Fight the New Drug

    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_16k_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
    jav
    0.38
    habt
    0.37
     распространен
    0.36
    eban
    0.36
    udal
    0.35
     ď
    0.35
    除去
    0.35
    ți
    0.35
    ContainsKey
    0.35
    QH
    0.35
    POSITIVE LOGITS
     neuen
    0.88
     nové
    0.80
     neue
    0.79
     nuevos
    0.78
     nieuwe
    0.78
    新的
    0.77
     nuovi
    0.77
     nuove
    0.75
    ใหม่
    0.74
     nuevas
    0.74
    Activations Density 0.129%

    No Known Activations