© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5678
    Prev
    Next
    INDEX
    Explanations

    impressive grand things

    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
    é
    0.53
    éssel
    0.52
    is
    0.50
    و
    0.50
    са
    0.49
    лк
    0.48
    п
    0.48
    юм
    0.48
    es
    0.47
    ب
    0.47
    POSITIVE LOGITS
    般的
    0.58
     unfold
    0.48
     onslaught
    0.46
     unleashing
    0.46
     unleashed
    0.45
     unrivalled
    0.44
    killers
    0.44
     החד
    0.43
     Итак
    0.43
     unleash
    0.43
    Activations Density 0.173%

    No Known Activations