© 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. 31766
    Prev
    Next
    INDEX
    Explanations

    ending sentences or common phrases

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

    explaining why something occurs

    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
     پرته
    0.44
    なんだ
    0.40
    )=>{
    0.39
    triggered
    0.39
    heritage
    0.38
    ка
    0.38
    ના
    0.38
    continuous
    0.37
    homemade
    0.37
    不会
    0.37
    POSITIVE LOGITS
    indruck
    0.45
     です
    0.44
     conci
    0.44
     Lue
    0.41
     truly
    0.40
     드
    0.39
    vive
    0.39
     Acres
    0.38
     Pleas
    0.38
     секунд
    0.38
    Activations Density 0.000%

    No Known Activations