© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8565
    Prev
    Next
    INDEX
    Explanations

    welcome and welcoming greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ส์
    2.27
    €˜
    2.04
    ik
    1.98
     debunk
    1.95
    us
    1.94
     És
    1.89
    ѕ
    1.89
    <0x0D>
    1.85
    )")
    1.82
     конф
    1.81
    POSITIVE LOGITS
     आईडी
    2.31
    FECT
    2.24
     asalamualaikum
    2.23
     izgled
    2.18
    Translatef
    2.17
     izvr
    2.17
     परहेज
    2.10
     kaya
    2.10
     làn
    2.07
     ומ
    2.06
    Activations Density 0.074%

    No Known Activations