© 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. 255158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    PP
    0.55
    吉
    0.47
    照
    0.45
    加载
    0.45
    trn
    0.45
     يرد
    0.45
     ppw
    0.45
    🌟
    0.45
     ملي
    0.44
     ي
    0.44
    POSITIVE LOGITS
    䪲
    0.53
    ாவில்
    0.48
    趼
    0.48
    獷
    0.44
    зва
    0.44
    אה
    0.43
    ила
    0.43
    三百
    0.42
    การ
    0.42
    嵓
    0.42
    Activations Density 0.001%

    No Known Activations