© 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. 232287
    Prev
    Next
    INDEX
    Explanations

    found what

    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
     Frequently
    0.47
    ក្នុង
    0.46
     theories
    0.46
    𝘀
    0.44
    ەڕ
    0.43
    き
    0.43
     Threshold
    0.43
    ardier
    0.42
     について
    0.42
    وٹ
    0.42
    POSITIVE LOGITS
    早上
    0.55
    中午
    0.47
     இதய
    0.47
    形成的
    0.46
     İlç
    0.46
     情况
    0.46
    मॉर्निंग
    0.46
     manhã
    0.45
    梼
    0.45
     kitabı
    0.45
    Activations Density 0.000%

    No Known Activations