© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38477
    Prev
    Next
    INDEX
    Explanations

    alphabet policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }=
    0.41
    reset
    0.41
    "@
    0.39
    {-
    0.38
    +{
    0.38
    _"+
    0.38
    otel
    0.38
    入手
    0.38
     asymmetry
    0.37
    initi
    0.36
    POSITIVE LOGITS
     souvent
    0.48
    ções
    0.46
    ações
    0.45
     ř
    0.44
     rattling
    0.43
    émon
    0.43
     réaction
    0.42
     بعض
    0.41
     çalışmaları
    0.41
     plupart
    0.41
    Activations Density 0.006%

    No Known Activations