© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118515
    Prev
    Next
    INDEX
    Explanations

    scene graph, effects of, available now, morrissey

    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
     tomen
    -0.92
    Цена
    -0.87
     perif
    -0.85
     offens
    -0.84
     fofo
    -0.83
     anormal
    -0.83
     equipa
    -0.82
     croissants
    -0.82
     atitude
    -0.82
    Всего
    -0.81
    POSITIVE LOGITS
    FC
    0.83
     bias
    0.76
     Belly
    0.75
    ный
    0.74
     instead
    0.74
    パン
    0.74
    𝑎
    0.73
    rg
    0.73
    辑
    0.73
     that
    0.72
    Activations Density 0.000%

    No Known Activations