© 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. 25502
    Prev
    Next
    INDEX
    Explanations

    returning from

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

    returning home

    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
     ठिकाणी
    0.45
    BCL
    0.44
    পাশে
    0.44
    出现的
    0.42
    BSITE
    0.42
    ">→</
    0.42
    ऐप
    0.41
    পানি
    0.41
     целях
    0.41
     posición
    0.40
    POSITIVE LOGITS
     ritorno
    0.93
    帰
    0.88
     верну
    0.84
     returning
    0.84
     return
    0.81
     retour
    0.80
     возвра
    0.78
    帰り
    0.78
     Returning
    0.78
     pulang
    0.78
    Activations Density 0.035%

    No Known Activations