© 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. 1606
    Prev
    Next
    INDEX
    Explanations

    compound phrases and named entities

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

    common phrases

    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
     कॉंग्रेस
    0.38
     txtbtn
    0.35
     BOARDSIZE
    0.34
    㿟
    0.34
    Triplet
    0.33
     پیغمبر
    0.33
    न्दावन
    0.33
    മ്ബ
    0.32
    𝙷
    0.32
     গুরুদেব
    0.32
    POSITIVE LOGITS
    ness
    0.32
    ies
    0.30
    </h5>
    0.30
     permeates
    0.29
    <b>
    0.29
     itself
    0.29
     refers
    0.29
    iin
    0.29
    <unused60>
    0.28
    </h3>
    0.26
    Activations Density 1.363%

    No Known Activations