© 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. 54016
    Prev
    Next
    INDEX
    Explanations

    record and season

    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
     modernen
    -0.92
     SQLException
    -0.89
    smoothing
    -0.86
    читал
    -0.82
     सिस्टम
    -0.82
    ようやく
    -0.81
    失礼
    -0.81
    机器
    -0.80
     medication
    -0.80
     allerede
    -0.80
    POSITIVE LOGITS
    artic
    0.88
     diversa
    0.84
     relentless
    0.82
    basis
    0.82
     Prior
    0.82
     다음
    0.82
    broad
    0.81
     fabulous
    0.81
    isse
    0.80
    énd
    0.80
    Activations Density 0.038%

    No Known Activations