© 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-TRANSCODER-262K
    4. 77576
    Prev
    Next
    INDEX
    Explanations

    Pet, Patron, petition, petrodollar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    永
    0.36
     oni
    0.35
    伸
    0.35
    Confident
    0.35
     mult
    0.34
     gira
    0.33
     ПО
    0.33
    辎
    0.33
    తం
    0.32
     Filtration
    0.32
    POSITIVE LOGITS
     Patron
    0.47
    Pet
    0.43
    pet
    0.41
     patron
    0.39
     PET
    0.39
     Petra
    0.39
    Pat
    0.39
    မျှ
    0.39
     pet
    0.39
     Pét
    0.38
    Activations Density 0.000%

    No Known Activations