© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14111
    Prev
    Next
    INDEX
    Explanations

    steps, crowns, arms, reports

    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
    hape
    0.38
    zeń
    0.38
    FFEE
    0.37
     confiance
    0.36
    氛
    0.36
    ーツ
    0.36
    cripts
    0.36
    IGA
    0.36
    醉
    0.36
     دوسرا
    0.35
    POSITIVE LOGITS
    lob
    0.38
     étro
    0.38
     Sic
    0.37
     Drak
    0.37
    Nos
    0.36
    お客様
    0.36
     freshwater
    0.36
     nasional
    0.36
     Katar
    0.35
    freq
    0.35
    Activations Density 0.000%

    No Known Activations