© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4358
    Prev
    Next
    INDEX
    Explanations

    e(commerce)/Class A/<?php/code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necessary
    -0.86
     arrep
    -0.83
    groupBox
    -0.80
     difficult
    -0.80
    ಿದ
    -0.79
     innehå
    -0.78
    WireFormatLite
    -0.77
    Élet
    -0.77
     SERIES
    -0.77
     increased
    -0.77
    POSITIVE LOGITS
     greyish
    0.84
    lots
    0.82
     Trabaj
    0.80
    Ī
    0.79
    possibly
    0.79
     (…)
    0.78
    などに
    0.77
     여러
    0.76
    部分を
    0.76
    LoL
    0.76
    Activations Density 0.001%

    No Known Activations