© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 589
    Prev
    Next
    INDEX
    Explanations

    reach out for help

    np_acts-logits-general · gemini-2.5-flash-lite

    action verbs denoting concrete actions or processes, especially phrasal/two‑word verbs and past or imperative forms.

    oai_token-act-pair · gpt-5Triggered by @igorkuztech
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     देखने
    0.52
    omaly
    0.52
     เมื่อ
    0.51
     смотре
    0.46
     -
    0.45
     от
    0.45
     มอง
    0.45
    ,
    0.45
     ยัง
    0.45
     และ
    0.44
    POSITIVE LOGITS
     zusätzliche
    0.98
    一个新的
    0.89
    出一个
    0.89
     zusätzlichen
    0.89
     zusätz
    0.89
    <unused1248>
    0.88
     svoju
    0.86
    निक
    0.85
     একখানি
    0.84
     svoje
    0.83
    Activations Density 4.231%

    No Known Activations