© 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. 246472
    Prev
    Next
    INDEX
    Explanations

    voyage experience, & Myrtle

    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
     উপায়
    0.55
     dépens
    0.55
     सूद
    0.55
    𝗘
    0.51
     संध्या
    0.50
    ethereum
    0.48
    ንሽ
    0.48
     смесь
    0.48
     ด่า
    0.48
    𝟯
    0.46
    POSITIVE LOGITS
    فوظ
    0.48
    早
    0.48
    屬
    0.47
    泳
    0.47
    早期
    0.46
    宏
    0.46
    ור
    0.43
     constitute
    0.43
    抱
    0.43
    дом
    0.43
    Activations Density 0.001%

    No Known Activations