© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165788
    Prev
    Next
    INDEX
    Explanations

    immigration, rent, shortage

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

    age distribution

    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
     mogli
    0.44
     Erick
    0.44
     அவற்ற
    0.44
    ;.
    0.43
    :.
    0.42
     o
    0.42
    ,+
    0.39
     the
    0.39
     basit
    0.39
    respective
    0.38
    POSITIVE LOGITS
    Всем
    0.48
     shortage
    0.47
     चौंका
    0.47
    ^{-(
    0.46
    Когда
    0.46
     ತೆಗೆ
    0.45
     keď
    0.45
    វិធី
    0.42
     महीने
    0.42
    Чтобы
    0.42
    Activations Density 0.001%

    No Known Activations