© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1553
    Prev
    Next
    INDEX
    Explanations

    create trackfunction character printeconomic black unitedencounter errors

    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
    들아
    1.35
    ﮢ
    1.31
    ﯾ
    1.28
    기고
    1.23
    LEA
    1.23
    omegranate
    1.23
    ﭜ
    1.23
    ﭥ
    1.22
    がたくさん
    1.20
     tcpHeader
    1.19
    POSITIVE LOGITS
     something
    1.65
    Something
    1.62
     Something
    1.58
    something
    1.51
     a
    1.50
     qualcosa
    1.49
    一款
    1.44
     elusive
    1.44
     een
    1.40
     یک
    1.39
    Activations Density 0.146%

    No Known Activations