© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236294
    Prev
    Next
    INDEX
    Explanations

    Spanish language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大利
    0.44
    )",
    0.44
    mortem
    0.43
    的国家
    0.43
     boot
    0.42
    €˜
    0.42
    טת
    0.42
    贓
    0.41
    éget
    0.41
    രിയ
    0.41
    POSITIVE LOGITS
     envoyer
    0.62
     leafy
    0.54
     sensory
    0.52
     unidos
    0.52
     conversar
    0.52
     blanches
    0.51
     exerce
    0.51
     presentaciones
    0.51
     pulmon
    0.50
     acoustics
    0.49
    Activations Density 0.000%

    No Known Activations