© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7815
    Prev
    Next
    INDEX
    Explanations

    starts with imp

    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
     It
    -2.84
     modernen
    -2.70
     frühen
    -2.64
     gemeinsamen
    -2.59
     früheren
    -2.56
     italienischen
    -2.53
     Their
    -2.47
    畯
    -2.47
     speziellen
    -2.41
     pero
    -2.39
    POSITIVE LOGITS
    橚
    4.06
    Ꮄ
    2.94
    埽
    2.89
     parachoque
    2.88
    涠
    2.84
    檍
    2.84
     umbro
    2.83
    
    2.77
    
    2.75
    웻
    2.69
    Activations Density 0.004%

    No Known Activations