© 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. 50508
    Prev
    Next
    INDEX
    Explanations

    verme, vermic, perme, perm

    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
    wikidata
    -0.81
     barbara
    -0.75
    врат
    -0.74
    nytt
    -0.73
    狀態
    -0.72
     zboží
    -0.72
     benda
    -0.72
     снова
    -0.72
     again
    -0.71
    മ്
    -0.71
    POSITIVE LOGITS
    ilion
    0.92
     Verm
    0.74
    varlak
    0.72
     permeable
    0.70
    cular
    0.70
    ious
    0.69
    žová
    0.69
     Deeper
    0.68
     perme
    0.67
    ý
    0.67
    Activations Density 0.027%

    No Known Activations