© 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. 42360
    Prev
    Next
    INDEX
    Explanations

    Fort Pierce or sanitation

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

    explanations and lists

    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
    说
    0.50
     foliis
    0.49
    奧
    0.48
    法国
    0.48
     calmer
    0.47
    歐洲
    0.46
    चिक
    0.46
    說
    0.46
    αλ
    0.45
    印度
    0.45
    POSITIVE LOGITS
     وبالتالي
    0.51
     Sanitation
    0.51
     রহিম
    0.50
     అలాగే
    0.46
     Sanitary
    0.45
    !
    0.44
    fahren
    0.44
    !!
    0.43
    🕔
    0.43
     sanitation
    0.42
    Activations Density 0.000%

    No Known Activations