© 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. 76234
    Prev
    Next
    INDEX
    Explanations

    realization was, wind shift, fall off

    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
    Jedi
    -0.98
    buti
    -0.90
     אבל
    -0.90
    breviations
    -0.84
    ➰
    -0.84
    但是
    -0.84
    (!_
    -0.83
     Channing
    -0.82
     screaming
    -0.82
    ＄
    -0.82
    POSITIVE LOGITS
     лишь
    1.27
    ◊
    1.09
    uscular
    1.05
    HEIGHT
    1.02
    无比
    1.00
    央视
    0.98
     início
    0.98
     bereiken
    0.96
    íguez
    0.96
    ఝ
    0.94
    Activations Density 0.003%

    No Known Activations