© 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. 128057
    Prev
    Next
    INDEX
    Explanations

    public function definitions

    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
    Vé
    -1.07
     conseguenze
    -1.04
     proposito
    -1.02
     parteci
    -1.01
    odotus
    -0.99
     torner
    -0.99
     billig
    -0.98
     zaterdag
    -0.97
     medier
    -0.97
     himmel
    -0.97
    POSITIVE LOGITS
     async
    1.15
     from
    0.95
    ABILIDAD
    0.94
    </strong>
    0.89
     socioeconomic
    0.86
    try
    0.85
     मान
    0.84
    est
    0.83
     stos
    0.83
    efel
    0.81
    Activations Density 0.013%

    No Known Activations