© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45390
    Prev
    Next
    INDEX
    Explanations

    read your

    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
     orphans
    0.46
     ditu
    0.45
    閬
    0.45
    အစိတ်အပိုင်း
    0.44
     laces
    0.44
    सामान्यीकृत
    0.44
     finalists
    0.43
    ي
    0.43
     mentors
    0.42
     rites
    0.42
    POSITIVE LOGITS
     Dodson
    0.42
     하여
    0.41
    数据显示
    0.41
     سع
    0.41
    BackgroundColor
    0.40
    звание
    0.40
    dense
    0.39
    ándose
    0.39
    doing
    0.39
    ox
    0.38
    Activations Density 0.005%

    No Known Activations