© 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. 57076
    Prev
    Next
    INDEX
    Explanations

    time, trigger, mounted, required, That, have

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

    application of concepts

    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
    3
    0.52
    王
    0.48
    眾
    0.48
    成员
    0.46
    成
    0.46
    قي
    0.45
    設定
    0.45
     Dự
    0.45
    Repo
    0.45
    лів
    0.44
    POSITIVE LOGITS
     bajar
    0.50
     kecil
    0.49
    phthalm
    0.49
     :}
    0.48
     paredes
    0.47
    :}
    0.47
    veratrol
    0.46
    ashov
    0.46
     ENVIRONMENTAL
    0.46
     bayi
    0.46
    Activations Density 0.000%

    No Known Activations