© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12413
    Prev
    Next
    INDEX
    Explanations

    private internal device code

    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
     superbes
    -1.14
    roën
    -1.09
    Über
    -0.99
    邉
    -0.98
    AnchorStyles
    -0.96
    iterranée
    -0.96
    ()])
    -0.96
    了好
    -0.96
    рет
    -0.95
     Votre
    -0.94
    POSITIVE LOGITS
     without
    1.09
     obtained
    0.96
     including
    0.96
    けれど
    0.95
    bano
    0.95
     before
    0.94
     containing
    0.92
     given
    0.91
     easily
    0.91
     after
    0.91
    Activations Density 0.001%

    No Known Activations