© 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. 67636
    Prev
    Next
    INDEX
    Explanations

    campus, Bergen, Slovakia

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

    highly motivated

    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
    та
    0.54
     otherworldly
    0.53
     противо
    0.50
    𝔯
    0.50
    querysearch
    0.49
     unrelenting
    0.49
    ೃ
    0.49
    <unused99>
    0.49
    𝕜
    0.48
    стов
    0.48
    POSITIVE LOGITS
     vij
    0.44
     secundaria
    0.42
     semestre
    0.42
     Vito
    0.42
    ராட்ச
    0.42
     البنات
    0.41
     الشباب
    0.40
    实践
    0.40
     Duque
    0.39
     primavera
    0.39
    Activations Density 0.000%

    No Known Activations