© 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. 160749
    Prev
    Next
    INDEX
    Explanations

    live video and street

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

    news or enrollment periods

    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
     आपला
    0.53
     établ
    0.52
     архі
    0.50
    도를
    0.49
     действие
    0.48
    怂
    0.48
     свое
    0.48
    攸
    0.48
     действия
    0.47
    ดำเนิน
    0.47
    POSITIVE LOGITS
     tropics
    0.45
     diagnostic
    0.42
     penyakit
    0.42
     edad
    0.41
     comforts
    0.39
     vignette
    0.39
     Mij
    0.39
     age
    0.39
     leng
    0.39
    uyi
    0.39
    Activations Density 0.000%

    No Known Activations