© 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. 39667
    Prev
    Next
    INDEX
    Explanations

    contacts

    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
    -2.80
    </i>
    -2.42
    }$
    -2.36
    2
    -2.22
    .“
    -2.16
    u
    -2.11
    or
    -2.03
    らしく
    -2.02
    {
    -1.99
     harán
    -1.91
    POSITIVE LOGITS
     opérés
    2.89
    medriver
    2.78
    摇了
    2.72
    Alongside
    2.55
    
    2.39
     contacts
    2.34
     granja
    2.33
     никогда
    2.19
    齟
    2.16
    contacts
    2.14
    Activations Density 0.003%

    No Known Activations