© 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. 221417
    Prev
    Next
    INDEX
    Explanations

    facility rental

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

    descriptive terms or qualifiers

    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
    는
    0.46
     appre
    0.45
     النمو
    0.45
     ث
    0.43
    隹
    0.42
    uminous
    0.42
    は
    0.42
    ired
    0.41
    娟
    0.41
    ίναι
    0.41
    POSITIVE LOGITS
    ि
    0.52
    正常的
    0.52
     referred
    0.50
     Mosque
    0.49
     Facilities
    0.49
     Bast
    0.49
     Patria
    0.48
    ⿶
    0.48
     Node
    0.47
     시설
    0.47
    Activations Density 0.001%

    No Known Activations