© 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. 59766
    Prev
    Next
    INDEX
    Explanations

    ASP.NET Html helpers

    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
    米的
    -2.98
    ).
    -2.73
     puntos
    -2.73
    呖
    -2.72
    
    -2.63
     bezpiecze
    -2.44
    เพื่อน
    -2.41
    迓
    -2.39
     ſou
    -2.38
    缡
    -2.36
    POSITIVE LOGITS
    0
    2.97
     решила
    2.91
    ?"
    2.84
    龵
    2.77
    {
    2.53
    A
    2.42
    E
    2.41
    s
    2.41
    龶
    2.39
    9
    2.34
    Activations Density 0.004%

    No Known Activations