© 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. 40-GEMMASCOPE-2-RES-262K
    4. 31509
    Prev
    Next
    INDEX
    Explanations

    state machine in python

    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_40_width_262k_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
    valve
    0.41
     valve
    0.41
    種
    0.40
    чиков
    0.39
     injector
    0.39
     trucker
    0.39
    trashButton
    0.39
    Ừ
    0.39
    ែ
    0.38
     coaster
    0.38
    POSITIVE LOGITS
    amatkan
    0.41
     Mathematics
    0.39
    üllen
    0.35
    的学生
    0.35
    高品質
    0.34
     الرياضيات
    0.33
    CreationFailed
    0.33
     تتم
    0.33
     дис
    0.32
    ременно
    0.32
    Activations Density 0.000%

    No Known Activations