© 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. 57376
    Prev
    Next
    INDEX
    Explanations

    pointer introduction

    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
    紧急
    0.46
     εδώ
    0.44
    oment
    0.44
     idé
    0.41
     inciso
    0.41
     εκεί
    0.41
    墜
    0.40
    ამდ
    0.40
     нужда
    0.40
    Essay
    0.40
    POSITIVE LOGITS
     instead
    0.46
     despite
    0.45
     Similar
    0.42
    ᴙ
    0.42
     مشابه
    0.42
     surprising
    0.40
     similar
    0.40
     resembled
    0.39
     sogar
    0.39
     대신
    0.39
    Activations Density 0.017%

    No Known Activations