© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13342
    Prev
    Next
    INDEX
    Explanations

    developed by or for

    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
    e
    -2.83
    u
    -2.47
    }
    -2.30
     if
    -2.30
    ⬮
    -2.11
    使った
    -2.09
    苹
    -2.08
    淙
    -2.05
    izielle
    -2.03
    剩下
    -2.03
    POSITIVE LOGITS
    但在
    2.34
     Previously
    2.33
     Apparently
    2.31
     Hardly
    2.28
     keinerlei
    2.27
        
    2.27
     Already
    2.20
    但是在
    2.19
    developed
    2.14
     Somewhat
    2.14
    Activations Density 0.017%

    No Known Activations