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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48851
    Prev
    Next
    INDEX
    Explanations

    interconnected data, cheaper fares, change range

    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
    낚
    0.38
     trademark
    0.38
    ggio
    0.38
     \
    0.38
     Mexican
    0.38
     mà
    0.37
     taff
    0.37
     artisanal
    0.37
    mathbb
    0.36
    uyendo
    0.36
    POSITIVE LOGITS
    ی
    0.44
    ضع
    0.43
    ുണ്ട്
    0.42
    ر
    0.42
     годах
    0.42
    ม
    0.42
    ᠩ
    0.41
    線を
    0.41
    rzeb
    0.40
     gå
    0.40
    Activations Density 0.008%

    No Known Activations