© 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. 27923
    Prev
    Next
    INDEX
    Explanations

    internationalization

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

    unique valuable paradises

    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
    markdown
    0.55
    💡
    0.53
    trigger
    0.50
    📔
    0.50
    ’
    0.50
    </code>
    0.48
    quis
    0.47
    </b>
    0.46
    💉
    0.46
    </u>
    0.45
    POSITIVE LOGITS
     každ
    0.52
    იან
    0.45
     κάθε
    0.43
    sburg
    0.43
    सेच
    0.42
     größten
    0.42
     länger
    0.42
     mieście
    0.41
    跻
    0.41
    現代
    0.41
    Activations Density 0.000%

    No Known Activations