© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130350
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or context

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

    actions related to code and strings

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Displacement
    0.52
     edible
    0.48
     Ababa
    0.46
     infine
    0.46
     yeast
    0.45
     unassuming
    0.45
     gek
    0.45
     l
    0.44
     versione
    0.44
     Ahab
    0.44
    POSITIVE LOGITS
    託
    0.51
    池
    0.49
    欄
    0.47
    抜き
    0.47
    段
    0.47
    สั่ง
    0.47
     требо
    0.46
    抽
    0.46
    })$-
    0.45
    牆
    0.45
    Activations Density 0.000%

    No Known Activations