© 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-16K
    7. 9847
    Prev
    Next
    INDEX
    Explanations

    actually, in fact, genuine

    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_16k_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
    蒈
    0.45
    㕝
    0.44
     bisogno
    0.43
     બાબ
    0.43
     emek
    0.41
    懈
    0.40
    浲
    0.40
    กี
    0.38
    िल्‍ली
    0.38
     carro
    0.38
    POSITIVE LOGITS
     actually
    0.98
    実際
    0.95
    actually
    0.92
    实际
    0.89
    实际上
    0.87
     sebenarnya
    0.87
     фактически
    0.84
     egent
    0.84
    實際
    0.81
    其實
    0.81
    Activations Density 0.460%

    No Known Activations