© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    a little confused

    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
     But
    -2.33
     The
    -2.16
     Another
    -2.11
     if
    -1.96
    見えます
    -1.94
    umpulan
    -1.80
    {
    -1.80
     last
    -1.80
     there
    -1.76
     There
    -1.73
    POSITIVE LOGITS
    </h2>
    2.16
    quelize
    2.02
    am
    2.00
    }$
    1.92
    ſchen
    1.88
    
    1.88
     modellen
    1.84
    ore
    1.84
     }</
    1.83
    仍在
    1.83
    Activations Density 0.008%

    No Known Activations