Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 2108
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    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_22_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
     алге
    0.37
     коюм
    0.36
    क्रिय
    0.35
     ರಚ
    0.33
     ́
    0.32
    стро
    0.32
     грани
    0.31
    তাল
    0.31
     персо
    0.30
    ឪ
    0.30
    POSITIVE LOGITS
     aforementioned
    0.45
     उक्त
    0.38
     ชอบ
    0.37
    కుండా
    0.37
     เช่น
    0.36
     আপনাদের
    0.35
    ดังกล่าว
    0.34
     ทั้ง
    0.34
    ชอบ
    0.34
     通过
    0.34
    Activations Density 4.624%

    No Known Activations