© 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. 100405
    Prev
    Next
    INDEX
    Explanations

    within one

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

    exploit or take advantage

    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
    ulated
    0.49
     inhibitors
    0.48
     connected
    0.48
     infantry
    0.46
     显示
    0.46
    ong
    0.46
     collective
    0.46
     증
    0.45
     ini
    0.45
    ibration
    0.44
    POSITIVE LOGITS
    쐞
    0.61
     cárcel
    0.57
    рода
    0.54
    ファイ
    0.52
    _{+}^{
    0.52
    חס
    0.52
    שׁ
    0.51
    かず
    0.50
    крема
    0.50
    淪
    0.50
    Activations Density 0.000%

    No Known Activations