© 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. 22-GEMMASCOPE-RES-131K
    7. 65896
    Prev
    Next
    INDEX
    Explanations

    defining entries in lists

    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_22/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
     lustige
    -0.93
    וּ
    -0.93
     archivio
    -0.91
    =="")
    -0.90
     lantaran
    -0.89
     Consultez
    -0.89
     any
    -0.88
    vuo
    -0.87
     deriva
    -0.86
     saisi
    -0.85
    POSITIVE LOGITS
    ickness
    0.99
     KI
    0.96
     and
    0.93
     etc
    0.90
    ained
    0.90
    愀
    0.90
     saludables
    0.90
     muhte
    0.90
     HMM
    0.89
    ucin
    0.89
    Activations Density 0.003%

    No Known Activations