© 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. 183291
    Prev
    Next
    INDEX
    Explanations

    population statistics

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

    objects, registration, enumeration

    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
    痙
    0.45
    ión
    0.44
    ché
    0.43
    括
    0.43
    colnames
    0.43
    写真
    0.43
    ंतु
    0.43
    catalyzed
    0.43
     बिल
    0.42
    =(\
    0.42
    POSITIVE LOGITS
     vien
    0.47
     painfully
    0.46
     PARTY
    0.44
     graveyard
    0.44
     Vienna
    0.44
     setter
    0.44
     CDU
    0.44
     party
    0.43
     تعتبر
    0.43
     ECHO
    0.43
    Activations Density 0.002%

    No Known Activations