© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8172
    Prev
    Next
    INDEX
    Explanations

    contractions and punctuation

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

    plotly.express as px

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    ‣
    0.41
    ????????
    0.40
    ֽ
    0.40
    ক্তি
    0.39
     $[
    0.39
    䀦
    0.39
    ٬
    0.38
    <unused2110>
    0.38
     ἡ
    0.38
    ǂ
    0.38
    POSITIVE LOGITS
     profane
    0.38
     Prud
    0.37
    ົບ
    0.36
    spired
    0.36
    记者
    0.35
    แป
    0.34
    化
    0.34
    nicki
    0.34
    დ
    0.34
    不可
    0.34
    Activations Density 0.015%

    No Known Activations