© 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. 116505
    Prev
    Next
    INDEX
    Explanations

    automotive terms and specific models

    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
    ﻹ
    -0.94
     Whilst
    -0.93
    🩹
    -0.92
     relic
    -0.91
    Alright
    -0.88
    oucí
    -0.88
    ▔
    -0.88
     saliv
    -0.88
     decken
    -0.87
    Titulo
    -0.86
    POSITIVE LOGITS
    Escal
    0.90
     Football
    0.89
    𝚒
    0.88
     merely
    0.85
    ray
    0.85
     employing
    0.82
    haften
    0.82
    decoded
    0.81
    と思いました
    0.80
     нынеш
    0.79
    Activations Density 0.021%

    No Known Activations