© 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. 31-GEMMASCOPE-2-RES-65K
    7. 47578
    Prev
    Next
    INDEX
    Explanations

    focus on, still important

    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_65k_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
     вы
    0.55
     Versorgung
    0.50
     Modo
    0.46
     Cadd
    0.46
     n
    0.43
    ंपासून
    0.42
    یدن
    0.42
     renting
    0.42
     weniger
    0.41
     residential
    0.41
    POSITIVE LOGITS
    CFLAGS
    0.48
    istory
    0.44
    before
    0.43
    ضافة
    0.42
    䒱
    0.42
    estine
    0.41
     Feria
    0.41
     utilizó
    0.40
    Startup
    0.39
    Critical
    0.39
    Activations Density 0.007%

    No Known Activations