© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1850
    Prev
    Next
    INDEX
    Explanations

    start, then, to, Chinese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     topsail
    2.27
    бли
    2.24
    ム
    2.12
    かの
    2.11
     wij
    2.07
    匐
    2.07
     Opens
    2.05
     spôsob
    2.04
    Wij
    2.03
    نن
    2.02
    POSITIVE LOGITS
    gült
    1.66
    7
    1.62
    คืน
    1.54
    sixth
    1.45
    9
    1.41
    orse
    1.39
    ท้าย
    1.36
    6
    1.29
    8
    1.28
    onesia
    1.26
    Activations Density 0.132%

    No Known Activations