© 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. 87832
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    profound results

    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
    ک
    0.48
    ಗ
    0.45
    adai
    0.43
    ޑ
    0.42
    ليا
    0.42
    thias
    0.40
    مثل
    0.40
    کسی
    0.40
     Thrive
    0.40
    "$
    0.40
    POSITIVE LOGITS
     我们
    0.49
     problème
    0.48
     문제
    0.48
     समस्या
    0.45
     विरोधी
    0.45
     conséquences
    0.45
     সম্মত
    0.45
     phenomenology
    0.45
     anhydride
    0.43
     probleem
    0.43
    Activations Density 0.000%

    No Known Activations