© 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-65K
    7. 17518
    Prev
    Next
    INDEX
    Explanations

    breakaway state

    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
    イ
    0.49
    鹿児島
    0.47
    શ
    0.45
    אי
    0.45
    ค
    0.45
    Preis
    0.45
    各
    0.43
    関
    0.43
    તે
    0.42
    デン
    0.42
    POSITIVE LOGITS
     الشهر
    0.47
     Them
    0.45
     Sond
    0.45
     Brun
    0.43
    тят
    0.42
     Legal
    0.40
     الهدف
    0.39
    DLE
    0.39
     Aim
    0.39
     Greece
    0.38
    Activations Density 0.001%

    No Known Activations