© 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. 41123
    Prev
    Next
    INDEX
    Explanations

    p followed by equals sign

    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
    骉
    -1.46
     菇
    -1.46
     Inhalten
    -1.45
     زیرا
    -1.45
    
    -1.37
     perché
    -1.34
     våra
    -1.34
    loyed
    -1.30
    ísmo
    -1.29
     hochzeit
    -1.29
    POSITIVE LOGITS
     through
    1.44
    𖥦
    1.44
    𖥧
    1.38
     there
    1.35
    s
    1.34
     junge
    1.34
     it
    1.31
     their
    1.30
     desde
    1.30
     cortas
    1.27
    Activations Density 0.023%

    No Known Activations