© 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. 14892
    Prev
    Next
    INDEX
    Explanations

    events held at or in

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

    events conducted or held

    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
     सामूहिक
    0.54
     când
    0.54
     Dön
    0.52
    ﻞ
    0.51
    জনের
    0.51
     Aufnahme
    0.51
    জনকে
    0.50
     Prü
    0.49
     BREAK
    0.49
     SI
    0.48
    POSITIVE LOGITS
    conduct
    0.82
     conducted
    0.72
    held
    0.68
    using
    0.60
     indoors
    0.60
    M
    0.59
     برگزار
    0.58
    within
    0.57
    Conduct
    0.57
     dưới
    0.56
    Activations Density 0.073%

    No Known Activations