© 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. 188347
    Prev
    Next
    INDEX
    Explanations

    delivered to

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

    words after specific verbs

    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
    з
    0.59
     จะ
    0.48
    च
    0.47
     ә
    0.46
    ats
    0.45
    AT
    0.45
    રૂ
    0.45
    и
    0.44
     quali
    0.44
     还
    0.44
    POSITIVE LOGITS
    ढ़े
    0.50
    槓
    0.49
    ㍍
    0.48
    来る
    0.46
    悖
    0.46
    urchase
    0.46
    伍章
    0.46
    ᱦ
    0.46
    ㅄ
    0.46
    न्देल
    0.45
    Activations Density 0.000%

    No Known Activations