© 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. 153390
    Prev
    Next
    INDEX
    Explanations

    personal information

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

    synthesized sentence, cohesive image

    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
     împre
    0.52
     nomor
    0.46
    梨
    0.45
     helps
    0.44
     ford
    0.43
     enligt
    0.43
     umum
    0.43
     appointed
    0.42
     assures
    0.42
     İ
    0.42
    POSITIVE LOGITS
    {-#
    0.48
     ব্যক্তিগত
    0.46
    紝
    0.45
     personal
    0.44
     fluorescence
    0.44
    ました
    0.43
    personal
    0.42
     گئی۔
    0.42
     मुझसे
    0.42
    nia
    0.42
    Activations Density 0.001%

    No Known Activations