© 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. 10-GEMMASCOPE-RES-131K
    7. 85027
    Prev
    Next
    INDEX
    Explanations

    cord with subsequent words

    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_10/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
    vantaged
    -2.88
    艄
    -2.69
    聍
    -2.67
    铪
    -2.36
    鶫
    -2.36
    喁
    -2.28
    砹
    -2.27
    ኀ
    -2.25
     οποία
    -2.22
    
    -2.20
    POSITIVE LOGITS
    ’
    3.05
    —
    2.56
    -
    2.56
    Y
    2.47
    n
    2.45
    2
    2.31
    、『
    2.23
    –
    2.22
    -,
    2.09
    有著
    2.09
    Activations Density 0.010%

    No Known Activations