© 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. 56376
    Prev
    Next
    INDEX
    Explanations

    avoid long queues

    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
    elsior
    0.41
     ಮಾತ್ರ
    0.41
    ovll
    0.40
    ประมาณ
    0.39
    8
    0.39
    daar
    0.39
    Margaret
    0.38
     постро
    0.37
    ８
    0.37
    zez
    0.37
    POSITIVE LOGITS
     cashless
    0.49
     činjen
    0.46
     catastrophic
    0.45
     unforeseen
    0.44
     جسے
    0.43
     neonatal
    0.42
    غة
    0.42
    امات
    0.42
     outages
    0.42
     forfeited
    0.41
    Activations Density 0.014%

    No Known Activations