© 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. 234076
    Prev
    Next
    INDEX
    Explanations

    multilingual 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
     Otis
    0.54
    阱
    0.53
    \(
    0.50
    牲
    0.49
     nvp
    0.48
    ets
    0.46
    বার্ট
    0.46
    \
    0.46
    ي
    0.45
     Baird
    0.44
    POSITIVE LOGITS
     گری
    0.50
     सास
    0.48
     სახელ
    0.48
     ਸੰ
    0.45
     सर्वोच्च
    0.44
     दादी
    0.44
     اصلاح
    0.43
    gling
    0.43
    𝗨
    0.43
     каким
    0.43
    Activations Density 0.000%

    No Known Activations