© 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. 240634
    Prev
    Next
    INDEX
    Explanations

    health and progress

    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
     নিষেধাজ্ঞ
    0.52
     operación
    0.51
     aquel
    0.49
     নিষেধাজ্ঞা
    0.47
    ﻤ
    0.46
     incluyendo
    0.46
     oficinas
    0.45
     உள்ப
    0.44
     sadece
    0.44
     сколько
    0.43
    POSITIVE LOGITS
     Reaper
    0.47
     Complet
    0.46
     metabolized
    0.45
     astral
    0.45
     Elev
    0.45
     meditations
    0.44
     PTSD
    0.43
     Sagittarius
    0.43
    脿
    0.43
     Meditation
    0.42
    Activations Density 0.000%

    No Known Activations