© 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. 10124
    Prev
    Next
    INDEX
    Explanations

    consistent performance

    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
     sogenannten
    -2.02
     magnificent
    -1.94
     gesuchten
    -1.92
    阏
    -1.85
     nuevos
    -1.85
     üblichen
    -1.85
    皷
    -1.84
     picturesque
    -1.83
     nowy
    -1.81
     monstrous
    -1.79
    POSITIVE LOGITS
    '
    2.02
    ),
    1.69
     –
    1.59
    ！(
    1.59
     gives
    1.58
     encuentre
    1.52
    ent
    1.51
    ti
    1.49
    
    1.48
    𝙷
    1.48
    Activations Density 0.013%

    No Known Activations