© 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. 202252
    Prev
    Next
    INDEX
    Explanations

    forfeiture activity and payouts

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

    horror movie fanatics

    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
    경제
    0.47
    льну
    0.42
     ব্যবস্থাপনা
    0.42
    ản
    0.42
    świet
    0.41
    icherheit
    0.41
    绣
    0.40
    력
    0.39
    asketball
    0.39
     సామ
    0.39
    POSITIVE LOGITS
    ﻭ
    0.55
     only
    0.52
     allow
    0.50
     seaw
    0.48
     każ
    0.47
     manoe
    0.46
     cams
    0.45
     rates
    0.45
     todas
    0.45
     comme
    0.45
    Activations Density 0.001%

    No Known Activations