© 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. 22-GEMMASCOPE-RES-131K
    7. 14133
    Prev
    Next
    INDEX
    Explanations

    cardinal directions in addresses

    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
     will
    -1.36
     
    -1.30
     purported
    -1.24
    <bos>
    -1.20
    0
    -1.17
    нні
    -1.16
     wich
    -1.16
     következő
    -1.11
     biggest
    -1.10
     cripto
    -1.09
    POSITIVE LOGITS
     chré
    1.33
    Према
    1.30
    ണം
    1.28
    ℉
    1.27
    hető
    1.26
     färg
    1.25
     \%(
    1.25
     låter
    1.25
     fungerar
    1.23
     serupa
    1.23
    Activations Density 0.009%

    No Known Activations