© 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. 6852
    Prev
    Next
    INDEX
    Explanations

    storytelling and concepts

    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
    ad
    0.53
    Family
    0.45
    little
    0.44
     కుటు
    0.44
     ($\
    0.44
     drafted
    0.44
    com
    0.44
     (†
    0.44
     زد
    0.43
     सीताराम
    0.43
    POSITIVE LOGITS
     tanpa
    0.45
    홀
    0.41
    第一次
    0.41
    种
    0.41
    মহ
    0.40
     convention
    0.39
    дено
    0.39
     CAPACITY
    0.39
    اهد
    0.39
    ולי
    0.38
    Activations Density 0.016%

    No Known Activations