© 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. 233424
    Prev
    Next
    INDEX
    Explanations

    social integration, political contexts

    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
     మి
    0.54
    ня
    0.52
     lasci
    0.48
    Ს
    0.48
    .
    0.48
     communist
    0.47
     socialist
    0.47
    🍨
    0.46
    })
    0.46
    🛎
    0.45
    POSITIVE LOGITS
    eram
    0.50
     Households
    0.47
    ેશન
    0.45
     Balliye
    0.42
     ၁
    0.42
     Behör
    0.41
    otus
    0.41
     períodos
    0.41
    enal
    0.41
     દરમ
    0.40
    Activations Density 0.001%

    No Known Activations