© 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. 218014
    Prev
    Next
    INDEX
    Explanations

    affairs and transactions

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

    turret, doors, mimicking, cause

    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
     possessions
    0.45
    eous
    0.44
     totalled
    0.43
     सुगंध
    0.43
    asted
    0.41
     surpasses
    0.41
     logro
    0.41
    Dad
    0.40
     vented
    0.40
    ಠ
    0.40
    POSITIVE LOGITS
     umożliw
    0.53
     by
    0.50
    کار
    0.49
     activer
    0.47
    لوب
    0.47
     například
    0.47
     ändern
    0.47
     lizenz
    0.46
     zuletzt
    0.46
    是一个
    0.46
    Activations Density 0.000%

    No Known Activations