© 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. 64521
    Prev
    Next
    INDEX
    Explanations

    compatible earth sign

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

    incomplete or sometimes Xcode

    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
     gestão
    0.44
     weren
    0.44
     kế
    0.43
     muchísimo
    0.42
    冊
    0.41
    chte
    0.41
     بهذا
    0.41
     hỏi
    0.41
     текст
    0.41
     đựng
    0.41
    POSITIVE LOGITS
     İm
    0.51
    ponente
    0.42
     Inhib
    0.41
    یکه
    0.40
    یم
    0.40
    尒
    0.40
    ⼯
    0.40
     সক্র
    0.40
    ایه
    0.40
     テレビ
    0.40
    Activations Density 0.000%

    No Known Activations