© 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. 6278
    Prev
    Next
    INDEX
    Explanations

    to be

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

    to be able to

    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
     by
    0.43
     絵
    0.43
    চূ
    0.42
    imenta
    0.42
     以上
    0.41
     peered
    0.41
    ারিত
    0.41
     両
    0.40
    最後に
    0.40
     চেপে
    0.39
    POSITIVE LOGITS
     सिंहासन
    0.43
    ॥
    0.43
     hukum
    0.42
     రచ
    0.42
     проведение
    0.41
    ประตู
    0.41
     заявление
    0.40
     examining
    0.40
    こちらの
    0.40
     clos
    0.40
    Activations Density 0.000%

    No Known Activations