© 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. 74940
    Prev
    Next
    INDEX
    Explanations

    Objective-C method selection

    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
    V
    -2.27
    "
    -2.09
    1
    -1.98
        
    -1.93
    s
    -1.92
    n
    -1.91
    </h3>
    -1.90
     
    -1.88
    m
    -1.87
    u
    -1.84
    POSITIVE LOGITS
     you
    2.27
    gucig
    1.94
    雱
    1.88
    guantes
    1.82
    carteles
    1.80
     wilayah
    1.80
    えました
    1.78
    ޏ
    1.77
    pulsera
    1.76
     daerah
    1.75
    Activations Density 0.005%

    No Known Activations