© 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. 119907
    Prev
    Next
    INDEX
    Explanations

    location and containment

    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
     BUT
    -1.50
            
    -1.48
     But
    -1.39
    cademia
    -1.32
     AGAIN
    -1.25
     pianist
    -1.25
     MUCH
    -1.23
    餮
    -1.23
     nude
    -1.23
        
    -1.22
    POSITIVE LOGITS
    图源
    1.38
    zości
    1.38
     mendapatkan
    1.37
     you
    1.36
    不一定
    1.35
     there
    1.35
    بدون
    1.34
     here
    1.34
    袛
    1.33
    diseño
    1.30
    Activations Density 0.013%

    No Known Activations