© 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. 182972
    Prev
    Next
    INDEX
    Explanations

    increasing this

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

    current state or status

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ）
    0.52
    ；
    0.47
    猫
    0.47
    the
    0.46
    ．
    0.45
    )....
    0.43
    ;
    0.43
    因
    0.43
     brie
    0.42
    略
    0.42
    POSITIVE LOGITS
     ज़ि
    0.45
    DEBUGFS
    0.44
    lsulfanyl
    0.43
     операций
    0.43
    manı
    0.42
     Yardım
    0.42
     ആരാധ
    0.41
     प्रतिष्ठा
    0.41
    𝗔
    0.41
     tampil
    0.41
    Activations Density 0.000%

    No Known Activations